Marketing teams often operate with a hidden skepticism tax.
Because they don’t fully trust their data, they spend enormous amounts of time cleaning spreadsheets, reconciling conflicting reports, and second-guessing both attribution models and AI outputs.
The result is slower execution, weaker alignment across teams, and decisions built on uncertain foundations.
Take branded search. It often gets credit for conversions that were likely to happen anyway, like a revolving door taking credit for everyone who enters a building. That gap between correlation and causation points to a much larger problem in modern marketing: too many teams operate on incomplete, fragmented, or low-confidence data.
The solution isn’t simply collecting more information. It’s building data foundations marketers can actually trust — verified identities, unified reporting, cleaner pipelines, and measurement frameworks designed to separate signal from noise.
Below is a breakdown of the core concepts behind those foundations and the types of data environments they create.
Probabilistic vs. deterministic
Let’s look at a simple example to illustrate probabilistic vs. deterministic: a coffee shop loyalty app.
When a customer logs in and orders, you know it’s Sarah — that’s deterministic. But when someone on the same Wi-Fi network browses your menu without logging in, you might guess it’s Sarah based on device and location signals — which is probabilistic. Both are useful, but you wouldn’t send a “Happy Birthday, Sarah!” push notification based on a guess.
It can be effective to show clients data-to-confidence mapping using the identity confidence thermometer:
Identity confidence thermometer
Deterministic is at the top (100% confidence), while the confidence level grades down through probabilistic levels as you get to the bottom of the thermometer (IP match, device fingerprint, behavioral inference, etc.).
Imagine three people describing the same elephant. Marketing touches the trunk and says, “It’s a hose.” Sales grabs the leg and says, “It’s a tree.” Finance feels the tail and says, “It’s a rope.” That’s what siloed data does to ROI reporting. A holistic data spine, by contrast, means everyone’s looking at the whole elephant.
Here’s a more concrete example: A B2B SaaS company is running LinkedIn ads. Marketing counts 5,000 form fills. Sales only sees 2,000 in the CRM because duplicates and junk leads have been filtered out. Finance counts 1,200 closed-won and attributes them to organic because UTMs broke. That’s three different teams, each with a different “truth” — zero confidence.
This illustration shows what this looks like in comparison:
Siloed vs. holistic — the three-truths problem
On the left side, we have three disconnected boxes: Marketing, Sales, and Finance. Notice that each shows a different number for the same campaign. Conversely, the right side shows all three boxes feeding into a single “Identity spine” bar that outputs a single agreed-upon number.
Third, first, and zero-party data
Consider the process of buying a house.
Third-party data is a neighbor who says, “I think they’re looking to move” — it’s just gossip.
First-party data is the realtor who sees them attend three open houses — it’s observed behavior.
Zero-party data is the buyer filling out a form and saying, “I want a three-bedroom house in Oakland for under $900,000” — it’s stated intent.
As cookies disappear, marketers are essentially moving from widely available gossip to less frequent but far more valuable direct conversation.
The analogy I like to use here is a kitchen where you never throw anything out. The fridge is packed, but half of what’s in it has expired. You often spend 20 minutes digging for the one ingredient you need, and occasionally you cook with something that’s gone bad.
This mess of a kitchen represents “big data.” Lots of information is easily accessible, but it’s nearly impossible to make sense of or have confidence in its accuracy.
“Correct data,” by comparison, is a curated pantry: Fewer items, all fresh, all labeled, and everything within reach is usable.
Here’s a direct example for all of us marketers: Feeding an AI model 500,000 rows of CRM data sounds impressive until you realize 30% are duplicate contacts, 15% have outdated emails, and the revenue field uses three different currency formats. The worst part is that the model doesn’t get smarter — it confidently sends you in the wrong direction (or spinning in circles).
Here’s a side-by-side comparison of two data pipelines.
Big data vs. correct data pipeline
The left is a firehose dumping raw data into a “swamp” (messy, murky, and opaque). On the right is the same firehose passing through a filter (validation, deduplication, formatting) into a clean reservoir. This filter is the “confidence layer.”
Correlation vs. causation
You’ve probably heard this juxtaposition a lot, both inside and outside the marketing context. In marketing, the classic example is that branded search always looks like the best-performing channel because people Google your name right before they buy. That’s like giving the revolving door credit for everyone who enters the building.
Correlation says, “People who walked through the door became customers.” Causation asks, “Would they have come in regardless of the door?”
Incrementality testing is the fix.
At a high level, you hold out a group from seeing your ads and compare their conversion rate to the exposed group, which should be similar in size and composition (e.g., similar geos). If the holdout group converts at nearly the same rate as the exposed group, your ads were just taking credit, not creating demand.
Here’s an example of a classic misleading view (branded search with sky-high ROAS) next to the incrementality-adjusted view (branded search deflated and prospecting channels elevated).
Correlation vs. causation ROAS
Essentially, this is a side-by-side comparison of what your dashboard says vs. what actually worked.
Those are the main data foundations used to build confidence across teams:
Identity confidence thermometer: From probabilistic (low confidence) to deterministic (high confidence).
Siloed vs. holistic: From siloed data (low confidence) to holistic (high confidence).
Data trust pyramid: From third-party data (low confidence) to first- and potentially zero-party data (high confidence).
Big data vs. correct data pipeline: A swamp producing “confidently wrong” AI outputs (low confidence) versus an added filter producing reliable outputs (high confidence).
Correlation vs. causation ROAS: From identifying relationships (low confidence) to establishing cause using a scientific framework (high confidence).
The confidence layer maturity spectrum
AI can handle countless tasks. But strong decision-making still depends on experienced marketers with good judgment. These data foundations help you move closer to that.
AMD’s Ryzen 7 X3D CPUs have all received price drops in the UK Only a few months have passed since the release of AMD’s Ryzen 7 9850X3D (review here), and the CPU is already available at a discounted price. In fact, all of AMD’s currently available Ryzen 7 X3D CPUs are now available at lower […]
Newegg is hosting a special bargain sale for the AMD Ryzen 9800X3D. By using a special promo code, you will be able to purchase this strong gaming CPU for a 16% discount and net a free Corsair CX750M power supply that's worth $64.99.
IBASE Technology Inc., a leading manufacturer of embedded and edge computing solutions, unveils the ES1002 Edge AI Server, a high-performance platform engineered to accelerate next-generation edge AI and data-intensive applications. Powered by AMD EPYC Embedded 8004 (Siena) series processors, the system delivers up to 64 cores and 128 threads, enabling efficient real-time analytics, AI inference, and large-scale data processing at the edge.
With support for up to six DDR5-4800 RDIMM slots with a maximum capacity of 576 GB ECC memory, along with five PCIe Gen 5 x16 slots, the ES1002 provides exceptional computing power and scalability for demanding workloads. It features a 4U rackmount chassis design with a spacious internal layout that significantly improves thermal efficiency and overall system stability. This robust architecture is ideal for long-duration, high-load operations in mission-critical environments. In addition, multiple PCIe expansion slots enable flexible integration of network interface cards, GPUs, and a wide range of AI accelerator cards, allowing the system to adapt to diverse edge AI deployment requirements.
Wacom today announced the Wacom Art Pen 2, a rotation-sensitive pen designed for digital artists and creative professionals seeking precise, expressive control in their digital workflows.
Expressive Control with Barrel Rotation
Building on the legacy of the original Wacom Art Pen (KP701E), the new Wacom Art Pen 2 continues to offer 360° barrel rotation and brings this capability into Wacom's latest pen technology. With compatible brushes, pens, and cursors, it can respond not only to pressure and tilt but also to the pen's rotational angle (when used with supported software). The Wacom Art Pen 2 enables artists to vary the thickness and character of their lines simply by rotating the pen in their hand—much like how traditional artists adjust the angle of a pencil, flat brush, felt marker, or calligraphy pen to achieve different expressive effects. This intuitive control allows for a more natural and dynamic drawing experience that closely mirrors the versatility of familiar traditional tools.
DeepComputing today announced the official launch of the DC-ROMA RISC-V Mainboard III for the Framework Laptop 13, marking a major milestone in bringing practical, high-performance RISC-V computing into a modular laptop form factor. Starting at $699, the new mainboard represents a significant step toward making RISC-V a developer-ready, everyday computing platform—combining open architecture, modern performance, and seamless integration with the Framework ecosystem.
Built on the RISC-V architecture and designed for full compatibility with the Framework Laptop 13, the DC-ROMA RISC-V Mainboard III is powered by the SpacemiT K3 RISC-V AI SoC—the world's first RISC-V SoC to support the RVA23 profile. This standardization milestone helps provide a more consistent software target for developers, accelerating ecosystem maturity.
The crowd did not take the comments quietly. What began as scattered murmurs quickly built into loud, sustained boos. Caulfield paused, visibly reacting to the response. "Oh, what happened?" she said, turning with her hands out. "Okay, I struck a chord. May I finish?" At least one person in the...
The fastest gaming processor has now hit one of the lowest prices ever and comes with a free power supply to power your rig. Newegg Bundles Corsair CX750M Power Supply With AMD Ryzen 7 9800X3D at Just $419 The world's fastest gaming processor is once again at an all-time low. Since the launch of Ryzen 7 9850X3D, the Ryzen 7 9800X3D has been listed for around $450 or lower on major retailers, but sometimes it slips below $430. Once again, the processor is available at $419 on Newegg, but this time with a free component. AMD Ryzen 7 9800X3D at […]
This might be the first time NVIDIA is giving away a game with a 60-class card in the RTX 50 series. NVIDIA Bundles 007 First Light With GeForce RTX 50 Series; GeForce RTX 5060 Ti Also Included Along With Higher-End SKUs In around two weeks, the 007 First Light will be available on Steam, but users have the option to pre-order the game now. It's currently listed at $69, and being a popular triple-A title, the game is already attracting significant attention from gamers. This is why NVIDIA has collaborated with IO Interactive A/S to provide a free game code […]
Back in December 2025, it was widely reported that PlayStation Network accounts could be easily hacked even with 2FA and passkey protection due to how account ownership is verified by PlayStation support. Hackers need only a transaction number to claim ownership of an account, effectively bypassing all digital security layers. Despite these reports, this security issue still hasn't been properly addressed, as the same user who originally reported the flaw has had their account hacked again. "Do you remember the hacking of my PlayStation account that went viral around the world and Sony still hasn't fixed? I got hacked again […]
BioShock creator Ken Levine was interviewed by IGN as part of the publication's IGN Icons series, and he shared his opinion on the evergreen debate between realistic and stylized graphics. Levine reckons that relying on cutting-edge technology to deliver realistic graphics is expensive and also doesn't age as well as a more stylized approach. I don't think we've ever been a company that was like, oh my God, we need the latest and greatest technology. In the rendering space we've never been a company; outside of SWAT 4, we never really tried to do ultrarealism in our games. It's expensive, […]
Save over $250 on this Newegg combo deal that nets you the AMD Ryzen 7 9850X3D with an Nvidia GeForce RTX 5070 Ti graphics card from Gigabyte, now just $1,264.99.
The EU is planning an undersea cable that goes under the North Pole to connect to Asia. This route avoids geopolitical hotspots like the Red Sea and the Persian Gulf but will have to weather the harsh Arctic.
Aurora consists of two products built for agencies. ContentPulse is a per-client voice engine that turns one podcast or blog into 50+ platform-native posts in each client's voice. ClientPulse is the agency's collective memory, queryable with every email, meeting, and invoice in one vault, plus an agent that flags churn over 60 days early.
Meteorra AI helps YouTube, TikTok, and Instagram creators identify the markets and audience segments most likely to respond to their content before publishing. It generates market-aware metadata, including tags and hashtags, audience targeting insights, and timing recommendations. It also suggests titles, visuals, and thumbnail ideas to improve click-through. Use the creator pack to position content clearly, improve discovery, and publish with confidence.
All eight episodes of steamy teen drama Off Campus are now streaming on Prime Video. But did you spot the platform's emotional promo for your next heartbreaking binge?
For years, SEOs measured visibility through keywords, rankings, links, and click-through traffic.
Those things still matter.
But the return signal has weakened, especially at the top of the funnel.
The bigger shift is how your prospective customers solve problems. Buyers* no longer have to compress a question, constraint, fear, or doubt into a keyword. They can ask AI systems in natural language, add context, and explain what they need in order to make the best decision for their situation.
If teams sleep on that shift, they’re going to wake up with visibility nightmares they can’t explain with old SEO metrics.
That changes the job for link builders.
The goal was never just more links. Link builders needed to earn visibility on converting pages.
Now, we have to move closer to the decision: what information a buyer needs, whether that information exists, and which sources AI systems can retrieve, trust, and use.
Link building has to evolve into citation optimization.
*Buyer is shorthand for the practitioners, stakeholders, and decision participants trying to solve a problem your offering can help address.
AI search changes what SEO visibility means
Still hyper-focused on top-of-funnel visibility?
That era isn’t gone, but it doesn’t create the same impact.
Ranking for broad, buyer-relevant topics can still help. So can visibility in the related searches and sources AI systems pull from when a decision-stage prompt needs fresh information.
SEO fundamentals still matter: useful content, trusted references, authority, source consistency, clarity, and strong links.
But the old chain (earn the link, support the ranking, get the click, prove the impact) has weakened.
SEO and link building built an entire operating model around keywords because keywords were the unit of measurement available to us.
But keywords were always a compressed version of the real problem.
A person had a question, a constraint, a fear, a decision to make, or a job to get done. To use search, they had to translate that into a keyword.
AI changes that behavior. People can ask in natural language, add context from prior interactions, and explain what they’re trying to solve, what they already know, and where they’re stuck.
That sounds simple, but it creates a deeper mindset shift for SEO teams. The work has to shift from ranking for the keyword to helping the person solve the underlying problem.
The business ranks for loads of keywords and gets millions of site visitors.
Then someone within the organization asked a specific question tied to a buyer’s pain point and service, and the brand didn’t rank among the answers.
Competitors did.
Google’s AI Mode didn’t surface them because it lacked sufficient context to confidently identify, cite, include, and recommend their brand as a leading solution for those specific buyer questions.
These aren’t keyword-based questions. They’re buyer-side questions that used to surface only during sales calls: clarification, fit, use case, proof, and implementation questions that buyers ask once they’re deep into consideration and due diligence.
Traditionally, that information lived in sales reps’ heads and a few internal sales enablement assets. They’d use context during calls to figure out the buyer’s specific needs and match them to the service.
The link builder’s job (yes, it’s up to us… we’re still frontline with publishers) is now to pull that information out of the organization and use it in places that AI tools review for answers.
Not just backlinks.
This means link builders need access to key sales and implementation diagnostics insight.
Once those questions surface, keyword coverage alone won’t do it.
It can show demand, but it won’t show what a buyer needs to understand before they trust a recommendation. And it won’t cover the questions buyers don’t know to ask (which we call FLUQs).
That missing decision-level information is what AI systems need to find before they include, compare, or cite the brand.
Citations start before the answer
If keyword coverage misses the buyer’s decision questions, where do AI systems get the material to answer them?
It won’t show the exact prompts buyers type. No one gets that data. And recent research suggests synthetic prompts can still give a useful signal when they model real buyer intent, but we shouldn’t treat one run – or 100 – as the truth.
You start by asking, “When we ask a prompt that represents a buyer problem, what sources does the system reach for?”
That’s where the link-building work changes.
You need to look at the cited pages in those answers and ask whether they give the system enough detail to answer without guessing:
Do they explain the offer?
Do they compare options?
Do they show the use case?
Do they include the proof?
The source mix changes by prompt, industry, and intent.
At the bottom of the funnel we frequently see AI tools cite LinkedIn, YouTube, third-party comparison pages, microsites, and TONS of content from competitors or in-market vendors in answers to buyer prompts. In some segments we’re seeing government documentation and guidance
In-market vendors often make up the biggest citation bucket.
AI systems use what they can retrieve and apply quickly, with minimal compute (much like humans). A page with the table, comparison, framework, or structure already built gives the system something to use.
Your job is to earn links and improve the material AI systems may reference before they decide which brands belong in the answer. Citation optimization starts before the answer.
Important note: Don’t over read a single prompt run. Track prompts multiple times to look for repeated gaps. If a brand disappears from a valuable prompt category, that absence gives you a place to investigate.
Citation optimization: The future state of link building
Citation optimization means identifying the pages and websites that influence AI answers, then improving how they mention your offering. Hence, the brand appears more consistently, more accurately, and in a better context.
A simple way to operationalize this approach is to remember PARSE:
For SEOs and link builders, the starting point is prompt-led source research:
Track the unbranded prompts that matter to the buyer’s problem.
Run them more than once.
Look at which pages and domains the system cites repeatedly.
Inspect those pages.
You should ask:
Which sources shape the answer?
Which ones compare options?
Which ones have a table, list, framework, or explanation the system can use?
Which ones mention competitors but leave you out?
Which ones mention you without enough context to explain why you belong?
This approach gives link builders a different kind of target list. Your goal isn’t only to secure another backlink. It’s to improve the source material that AI systems may use before they decide which brands belong in the answer.
That can mean adding the brand to a cited page, improving an existing mention, replacing a thin comparison with a clearer one, contributing a table, graphic, short explanation, or other asset chunk that gives the page more useful material to work with.
This still includes links.
We’re not leaving the link behind.
But a brand mention and anchor text alone is too thin.
You need anchor context: useful material around the link that helps a system understand the value of the mention.
Whether you’re in-house or working with link builders, you need to ask for more than a backlink.
Ask for a backlink plus anchor context: a useful piece of context that can help form an AI citation. At a minimum, that chunk should explain the offer, the use case, who it helps, and why it belongs in the answer.
That’s the first shift from link building to citation optimization and increased search AND AI visibility.
Cybersecurity researchers are calling attention to a new campaign dubbed GemStuffer that has targeted the RubyGems repository with more than 150 gems that use the registry as a data exfiltration channel rather than for malware distribution.
"The packages do not appear designed for mass developer compromise," Socket said. "Many have little or no download activity, and the payloads are repetitive,
Windows 11 isn’t just moving to WinUI 3; Microsoft’s also making WinUI 3 faster Microsoft is working to make Windows 11 faster and more responsive. Part of this effort is moving core Windows experiences to WinUI 3, Microsoft’s native UI framework. This change will make Windows’ UI more consistent and faster, while reducing memory usage. […]
The Razer Enki Gaming Chair, which has received critical praise for its comfy ergonomics, superb lumbar support, and durability, is currently having a 34% discount sale for its pink variant and similar price drops for other variants.
Google launched its "Googlebook" laptops yesterday, introducing a new intelligent platform that leverages Gemini AI, succeeding its Chromebook offerings. Initially, it was unclear what hardware Google would use for its upcoming laptop models. However, Intel announced that it has been collaborating with Google on these models, with Intel Core processors at the core of the platform. Google is likely to pair these laptops with Intel's latest Core Series 300 "Wildcat Lake" processors, which the company recently launched. This means that Googlebooks will feature an x86 platform based on Intel processors, with six CPU cores consisting of two "Cougar Cove" P-cores and four LPE "Darkmont" cores. They will also include an NPU 5 with 40 TOPS of INT8 data, an Xe display and media engine, and a GPU with up to two Xe3 cores, all built on Intel's 18A internal node.
However, Intel will not be the exclusive platform provider for Googlebooks. In an exclusive interview with Google VP John Maletis, ChromeUnboxed learned that Google has set strict requirements for its OEM partners, including specifications for CPU, memory, keyboard layout, and storage configurations for its upcoming devices. Since launch partners will also include Qualcomm and MediaTek, we can expect to see Arm-powered Googlebooks as well. Acer, ASUS, Dell, HP, and Lenovo will be participating in the launch of the new Googlebook lineup, with devices reportedly arriving this fall.
AMD has announced six new Ryzen PRO 9000 Series processors for commercial desktops and workstations, with two of them bringing 3D V-Cache to the PRO lineup for the first time. All six are AM5 parts targeting managed business deployments rather than the consumer market. The top-tier model is the Ryzen 9 PRO 9965X3D featuring 16 Zen 5 cores, 32 threads, up to 5.5 GHz boost, 128 MB of L3 cache courtesy of 3D V-Cache, and a 170 W TDP. Think of it as the workstation equivalent of the Ryzen 9 9950X3D, just under the PRO branding with the associated manageability and security features. A non-X3D Ryzen 9 PRO 9965 sits alongside it with the same 16 cores and 170 W TDP but 64 MB of L3 cache. The 3D V-Cache also extends down to the Ryzen 7 tier with the Ryzen 7 PRO 9755X3D sporting eight cores, 16 threads, up to 5.2 GHz, 96 MB of L3 cache, and a 120 W TDP. Rounding out the lineup are the Ryzen 9 PRO 9955 (12 cores, 120 W), Ryzen 7 PRO 9755 (8 cores, 120 W), and Ryzen 5 PRO 9655 (six cores, 120 W), all with 64 MB or 32 MB of L3 cache depending on the model.
The new additions sit above the existing 65 W Ryzen PRO 9945, 9745, and 9645 parts, giving AMD a higher-power PRO tier for workstation builds that need more headroom. The latest additions to the AMD Ryzen PRO 9000 Series lineup are scheduled to launch in the second half of 2026, with systems based on the new processors expected to begin shipping during the same period. AMD also noted that Lenovo ThinkStation P4 workstation is currently planned for availability in Q3 2026.
Leila Turner-Scott and her husband, Angus Scott, say their son Sam started using ChatGPT during his senior year of high school in 2023 for help with homework and troubleshooting computer issues.
Dragon's Dogma 2 had a successful launch back in March 2024, yet the second entry in the series did not receive the same amount of post-launch support as other Capcom franchises. While backend changes spotted on Steam last month suggest that something could be in the works, the silence surrounding the game is making most fans fear that, with director Hideaki Itsuno's departure, this could be it for the franchise. Thankfully, this doesn't seem to be the case, as CAPCOM will nurture the series, among others, for its long-term growth. In its latest financial report for FY26/3, the Japanese publisher […]
The ProArt RTX 5090 is inspired by the Founders Edition, but offers a 2.5-slot thickness, and a premium cooling solution. ASUS Quietly Rolls Out ProArt GeForce RTX 5090 32 GB GDDR7 OC, Featuring 2.5-Slot Design, Vapor Chamber Cooling, Liquid Metal for Enhanced Thermals The GeForce RTX 5090 Founders Edition got popular because of its 2-slot design that had a double-vented backplate for easier airflow. ASUS adopted the same approach for its ProArt GeForce RTX 5090 OC and delivered a slightly thicker, but more powerful graphics card. While ASUS already introduced it at the CES this year, the company silently released […]
Despite the lack of solid details, the Xbox Project Helix is set to be a very different system from its predecessors, lacking typical GPU customization and bridging the gap between console and PC gaming in ways yet to be revealed. According to a new report from Windows Central, the next-generation Xbox could be a digital-only system, but a project codenamed "Positron" could allow users to still play their physical discs with some form of disc-to-digital program. "Codename 'Positron,' from what we can tell, could be some form of disc-to-digital entitlement program," the report reads. "The details here are incredibly scant […]
Fresh details and apparent in-game dialogue for Assassin's Creed Hexe have surfaced online courtesy of leaker Rogue, with additional context from j0nathan, offering juicy details about the next installment in Ubisoft's flagship action/adventure series. The game's protagonist appears to go by Anika, with "Elsa" reportedly serving as a placeholder name, as "Jora" did for Eivor during the development of Assassin's Creed Valhalla, according to j0nathan. The big twist is that it seems Anika is a descendant of Claudia Auditore, Ezio's sister, which provides the narrative thread connecting Assassin's Creed Hexe to the Italian Brotherhood's legacy. The game's primary location is Würzburg, a city in Bavaria historically associated […]
Katie AI is an intelligent coaching system that helps organizations move from scattered AI experiments to structured, measurable adoption across every department. It gives each employee a role-based learning path, real-time coaching, and tool recommendations while standardizing workflows without stifling autonomy. It addresses typical AI adoption concerns with real-time coaching on best practices, hours of built-in AI training and ideas, ROI tracking, prevention of PII inputs, and usage tracking.
BEOK PLANET lets you create a metaverse avatar for your pet and share it with a community of pet lovers. Explore nearby content, follow others, send messages, and build your pet’s identity across a virtual world. BEOK PLANET combines discovery and social features so you can connect with fellow owners, showcase your pet’s persona, and engage through posts and messaging.
TCL's new-gen TVs got a strong review from us in the US — and now the UK version has a price, and it's very tempting, even compared to the best of OLED.
We explain the sneaky practice of bandwidth throttling, how to detect if your ISP is targeting your traffic, and how encryption can restore your streaming quality.
Google on Tuesday unveiled a new opt-in Android feature called Intrusion Logging for storing forensic logs to better analyze sophisticated spyware attacks.
Intrusion Logging, available as part of Advanced Protection Mode, enables "persistent and privacy-preserving forensics logging to allow for investigation of devices in the event of a suspected compromise," the company said.
The feature, it
P-Studio's Persona 4 Revival is targeting a February 2027 launch, at least according to leaker lolilolailo, who proved to be reliable when it comes to games published by SEGA/Atlus. In a brief post submitted on ResetEra, the leaker quoted a message that noted the similarity of Persona 4 with Persona 3, adding: Maybe even in the release month for the remake. Persona 3 Reload launched in February 2024 to rave reviews from critics (our own Chris Wray rated it 9 out of 10) and a very solid commercial performance. It was the fastest game in the series to become a […]
The Dark Pictures franchise has always touched on supernatural horror, but has remained ultimately grounded in the modern (or not-so-distant) past. This has changed with Directive 8020, a science fiction tale set a dozen light-years from Earth. After dropping the Dark Pictures anthology branding for the new title, has Supermassive Games truly brought something new to the medium, or is this an all-too-familiar take? Enter the Cassiopeia: an exploratory ship venturing to the far reaches of an alien planet called Tau Ceti f to see if this planet might be hospitable for human life. As major corporations sponsored science trips are […]
Mad Snake is a fast-paced arcade snake game for iPhone that reimagines the classic with smooth D-Pad controls and six escalating levels. Dodge static obstacles, chase time-limited green apples for triple points, outsmart an enemy snake, and grab fireball power-ups to torch anything in your way. Beat all six levels to unlock Mad Mode, an endless survival run for the highest score. The game includes 4 snake skins, Game Center leaderboards, haptics, offline play, and social sharing. Free to play with optional IAPs.
Amadezing lets you design standout social posts, presentations, and marketing assets with AI on mobile or desktop. Start from smart AI suggestions, then tweak layouts, colors, and copy to match your brand, or create from scratch with intuitive editing. It acts like an agentic marketing team, helping from planning through design while keeping you in control. Use it to boost productivity, ship campaigns faster, and maintain consistent branding across channels.
IvyForms is a WordPress form builder that lets you create fast, responsive forms using drag-and-drop, templates, and advanced conditional logic. You can connect submissions to mailing lists, CRMs, and payment gateways, and collect structured data without coding.
Built by the team behind WPAmelia, wpDataTables, and Trafft, IvyForms fits real-world WordPress workflows. It lets you embed forms with Gutenberg, Elementor, or Divi, block spam with reCAPTCHA and honeypots, and manage multi-page and conversational forms to boost conversions.
Breeze lets you send files and clipboard content between your devices on any platform without accounts or cloud. It discovers devices on the same Wi-Fi or hotspot, transfers directly at full network speed, and encrypts every transfer. Built on the open LocalSend protocol, Breeze works with millions of existing devices and runs even without internet. Core features are free forever; optional Pro adds auto-accept, trusted device management, favorites, and extra themes.
Following the recent reveal of the Epomaker HE75 V2, the budget peripherals maker has now revealed the updated Epomaker x Aula F1080 Pro V2 wireless mechanical keyboard. The updated keyboard has yet to launch on Epomaker's website, but in a recent livestream, Epomaker showed off some of the features of the new full-size mechanical keyboard. As with the previous F108 Pro, the F108 Pro V2 features a plastic gasket-mount case that's held together with clips, making it a bit more of a challenge for modders but likely reducing the BOM cost and final price of the keyboard itself. An exact launch date has not yet been announced, nor has pricing, but if it's priced at all like the existing F108 Pro, it will cost around $100. The livestream showed off a number of colors, including a pastel pink, a retro-themed beige with brown and black accents, and a version with a black case with smokey translucent keycaps.
In preparation for the release of the upcoming release of KDE 6.7, KDE 6.6.5 has officially launched, bringing with it some fixes for performance regressions introduced with the recent NVIDIA driver 595 update. Release 6.6.5 isn't a massive release for KDE, instead an update focused entirely on bug fixes, with the full list available in the official changelog. However, some of the biggest updates include improved color handling on NVIDIA GPUs and the removal of the CI/DCI external display option when users have HDR enabled—HDR, by definition, should be in control of brightness in order to function properly.
Another bug that was squashed with KDE 6.6.5 is a bug relating to the latest NVIDIA 595 driver, which appeared to be affecting users on Wayland and KWin across multiple distributions, with the Bugzilla thread on the matter featuring comments from users on both CachyOS and Fedora. The issue seemed to be related to multi-GPU setups, and such issues are not expected to happen on KDE 6.7, because the multi-GPU copy code has been rewritten to use Vulkan instead of OpenGL. Another issue that could be bothersome was that Spectacle, the KDE screenshot utility, would not properly copy screen captures. To correct this, the KDE developers changed the utility to stay open for a brief moment after taking a screenshot, allowing the system to correctly copy the image to the clipboard. Plasma 6.7 is slated to launch on June 16, 2026, and it is expected to be a much more substantial launch, with a new Union style engine based on CSS, the reintroduction of the famous Air and Oxygen themes, and improved session restore under Wayland.
NVIDIA CEO, Jensen Huang, is now confirmed to accompany President Trump on his China visit along with Elon Musk, Tim Cook & other tech execs. US President Trump's High-Profile China Visit Can't Be Complete Without The Country's Leading Tech CEOs, & That's Exactly Why NVIDIA's CEO, Jensen Huang, Has Boarded Air Force One US President Donald J Trump will visit China this week from 13th May to May 15th May. During this visit, Trump will meet Chinese President Xi Jinping. All eyes will be on this visit as it will mark the first time in nearly a decade that a […]
Intel has just confirmed that its chips will be powering Googlebook, a premium & powerful laptop that combines Android & ChromeOS under one hood. Google's Googlebook Laptops Will Be Powered By Intel CPUs In Premium & Powerful Designs A few hours ago, Google announced its brand new laptop lineup at its annual I/O event, called Googlebook. The new laptops are aimed to be premium and powerful devices designed for AI intelligence, such as Gemini. While Google isn't revealing a whole lot of details at the moment, what we know about Googlebook laptops so far is that they will offer a […]
Google gunning for the Apple MacBook Neo with its very own Googlebook was certainly not on anyone's bingo card while tuning in to watch the Android Show I/O edition earlier today. And yet, that's exactly what Google appears to have done, made all the more dramatic with a perfectly timed confirmation from Intel just moments ago, openly declaring that the Googlebook will be powered by its silicon, though we are not sure at this nascent stage if it's meant to be an exclusive arrangement. Googlebook increasingly looks like a synchronized effort to thwart the MacBook Neo, especially as Intel, ASUS, […]
VibeSnapper turns a single screenshot of your build into prioritized feedback and four copy-paste prompts you can use in vibe coding platforms or agents like Bolt, Claude Code, Lovable, or v0. It scores, analyzes, flags issues, and suggests next steps to enhance your project. It runs frontier vision models guided by an expert-curated playbook, so reviews stay sharp and aligned with your taste. Upload or capture a screenshot with your browser and try VibeSnapper for free today.
Elon Musk’s xAI chatbot is struggling to compete with similar artificial intelligence projects from OpenAI, Meta and Google, per the Wall Street Journal.
Neowiz, the game studio behind the 2023 standout, Lies of P, has officially confirmed in its Q1 2026 earnings report that the sequel to Lies of P is officially in full-scale development, although likely in the very early stages of the process, since parts of the report still list the game as being in "vertical slice," which is a stage of development in which the studio makes a small part of the game to develop a feel for what the rest of the game will feel like. A new job listing on the Neowiz website also sees the game studio hiring a developer to work in an art team at Round8 where they will "leverage generative AI technology to maximize the efficiency of the art production process and innovate the visual quality of games."
The report also reveals that there are two unannounced IPs in the prototype phase—one souls-like RPG, Project Windi, and another narrative-based RPG, Project Windi—both of which are slated to launch for both console and PC. The upcoming puzzle-platformer, Goodbye Seoul: Itaewon, a game published by Neowiz but developed by Jino Games, is slated for a PC release in the second half of 2026. Part of Neowiz's strategy going forward is to use new IPs to diversify into different genres, with the studio specifically mentioning action, social sim, and mystery.
KaraokeCrowd helps you find accurate karaoke events at bars, KTV rooms, and public stages. Browse a live map of thousands of upcoming nights, check which days venues host karaoke, and use your location to discover spots nearby. Every listing is community-verified. Contribute updates, connect with hosts and venues, and help manage listings to keep schedules reliable for everyone!
chat.dev lets you run Codex and Claude agents on dedicated cloud VMs that keep working after you close your laptop. Each agent gets an isolated Linux machine with a browser-based terminal, so you can type tasks, interrupt with Ctrl-C, and let jobs run 24/7. It auto-commits and pushes the full machine state to GitHub, gives each agent a Solana wallet for on-chain spend tracking and billing, and streams terminal I/O over WebSockets. Typical agents use 2 vCPU and 4GB RAM, with pricing around $0.008 per hour.
Lucas is a proactive personal assistant you text to get things done. It manages email and calendar, checks you in for flights, submits tasks, and helps keep habits on track. You can set up automations in plain English, use voice notes when busy, and connect over 100 apps so it can work across your tools. Lucas sends timely nudges, summarizes meetings, and coordinates routines right in iMessage.
With prices starting from AU$699, three new Kindle Scribe digital notebooks are up for pre-order in Australia, including the long-awaited Colorsoft version.
There is no governmental mechanism to pay for an AI agent that monitors a patient between visits, calls to check in, coordinates a housing referral, or makes sure someone picks up their medication. ACCESS creates that mechanism for the first time.
The newest Xbox Game Pass tiers appear to be specifically targeting the lucrative Chinese market, and is Microsoft also working on a disc-to-digital program?
Driftless helps you use your phone on purpose instead of on autopilot. When you unlock, it asks why you’re opening your phone, then a coach watches which apps you use and for how long, offering gentle nudges when you start to drift. You get clear, guilt-free insights into where your attention went. Built as a coach, not a blocker, Driftless pairs awareness with practical guidance so you can reclaim focus and build habits that stick. Join closed early access on Android.
Oylo transforms live video using AI in real time on every frame. Type a prompt, point a camera, and watch reality bend with no waiting or technical setup. It runs in your browser on desktop or mobile and works with built-in or external cameras, even remotely. You can be up and running in a minute without any design or technical skills, producing unique results. Integrations with Resolume Arena are coming soon for professional VJ setups. Current use cases include VJs at live shows, artists creating installations, streamers wanting unique camera effects, and people at parties.
JustVibe is an AI search engine that turns plain-language requests into live, interactive spaces you can use immediately. Describe your goal and it creates the data, logic, and UI to make it work, from trip planners and mood boards to schedulers and simulators. Refine results with prompts, explore popular spaces, and create custom workflows without code.
New controls in the company’s Family Center dashboard will build on Instagram’s existing Your Algorithm option, and additional alerts will provide more oversight.
Xbox's Forza Horizon 6 is slated to be one of this year's biggest games, and ahead of its launch, it's become a top seller on the PC gaming store Steam.
After 2026 saw the launch of several strong single-player games—Pragmata, Resident Evil Requiem, Crimson Desert, and Far Far West showing strong performance in terms of sales, Sega has just released its financial results for the year ending on March 31 (FY 2026), and it's not looking good for the gaming giant's live-service games. According to the results, Sonic Rumble Party showed poor performance, and there was a delay in some as-yet unannounced games. Most notably, Sega has officially cancelled its mystery "Super Game," citing no additional costs with associated with the game's cancellation. What exactly this super game was is unclear, but it was announced as far back as 2021 as a collaboration with Microsoft and would see Sega build a game using Microsoft Azure.
Sega had reportedly budgeted as much as $882 million for the development of the aforementioned "Super Game," and it was expected to bring in over ¥100 billion ($634.5 million converted). Following the game's cancellation, Sega says it will "review the positioning of the pillars for medium- to long-term growth" by lowering the priority of some free-to-play games. By lowering the GaaS development priority, it will be able to transfer over 100 personnel to its "Full Game" development team, meaning it will focus on more traditional game models, such as single-player narrative experiences for the upcoming year. Sega expects to increase Full Game sales going forward, although it still expects to see losses widen in the next year as a result of increased up-front investment in game development.
Razer, the leading global lifestyle brand for gamers, today announced the Razer Huntsman V3 Tenkeyless 8KHz, an analog optical esports keyboard built on the same competitive foundation as the Huntsman line.
Streamlined, focused, and purpose‑built, it brings Razer's core performance technologies into a tenkeyless form factor engineered to perform reliably straight out of the box—whether at home, on stage, or on the move.
Google devoted much of its Android Show event to Googlebook, a new operating system and product line designed to replace Chromebooks, with an emphasis on both local and cloud processing.
The Steam Community Market has been a hub for the massive online exchange of in-game items for years, supporting the game economy for over 13,000 games with items available on the market. However, as the number of listings has increased, so has the users' need for more detailed item listings, prompting Valve developers to enhance the capabilities of the Steam Community Market. In the latest beta launch, Steam is introducing larger and more detailed item listings, improved search functionality, better product filtering, and enhanced asset data.
Firstly, listings are becoming much larger with the expanded view, allowing a single listing to contain more images, longer descriptions, and even special notes for items with applied accessories and more. Users can now use the search function to scroll through the search results with a flip scroll.
Just 48 hours before the game's official launch, Subnautica 2 has seemingly leaked, with game repackers sharing their pirated versions of the game across sites like r/PiratedGames on Reddit. This leak follows the leak of Forza Horizon 6, which seemingly leaked via a game reviewer or influencer with pre-launch access to the game. This time, the developer, Unknown Worlds, has yet to comment on the apparent leak of Subnautica 2, but those who have played the leaked version of the game have posted screenshots and clips, which have now been archived in r/GamingLeaksAndRumours. It should also be noted that the original page hosting the leaked game files on GameDrive has already been taken down.
In the Reddit post archiving the game content, the poster claims that the leaker obtained a game code via game reviewers, so it seems as though one or more reviewers have been breaking NDAs in order to leak copies of the game in the open. A similar situation happened ahead of the recent launch of Capcom's Resident Evil Requiem. Following these leaks, there have been concerns that game developers and publishers could stop seeding game codes to reviewers ahead of launch, which would potentially result in less informed gamers who have no clear indication of quality before spending their hard-earned dollars on games. Unlike Forza Horizon 6, Unknown Worlds has already started allowing paying players to preload Subnautica 2 ahead of its May 14 launch.
Star Wars: Fate of the Old Republic has been out in the open now, with the game's director, Casey Hudson, formerly of BioWare, promising a pre-2030 launch in late 2025. Now, in a recent statement to Bloomberg about the upcoming game and a recent investment by NetEase veteran, Simon Zhu, Hudson has commented on the both the development process and scope of Star Wars: Fate of the Old Republic. Critically, Hudson says that "bigger isn't necessarily better," and explains his aversion to drawn-out games, saying that "if I'm excited about a game, and then I find out it's 200 hours long, even if I have no ambition to actually finish it, I wonder, if I put 20 hours in, will I even be out of act one?"
Hudson added that there will be ways to extend your fun in Fate of the Old Republic via replayability and alternative storylines that can be explored in subsequent play-throughs. He also commented on the development process, stating that "making games that take five or seven years—none of us want to do that," reiterating his previous commitment to a pre-2030 release for Fate of the Old Republic. On the topic of generative AI, Hudson had harsh words, calling the tech "creatively soulless," and rejecting its use in the game design and development process. The new Star Wars game will be receiving funding from Simon Zhu's newly announced holding company, GreaterThan Group, which was officially announced on May 12, 2026, and has a $40 million bank balance with another $60 million in funding commitments from "gaming and tech entrepreneurs."
Western Digital develops hard drives which spin down for lower power consumption while maintaining performance acceptable for hyperscale production workloads.
Apple has significantly upgraded the camera hardware on its iPhones, starting with introducing high-resolution 48MP sensors, to bringing telephoto units, and later this year, the company will make history by bringing variable aperture technology to the iPhone 18. However, none of these additions are useful if there’s little to no software control, which is why the latest report states that iOS 27 is bringing a major change that will cater to both casual and professional users. A more customizable Camera app is arriving on iOS 27, allowing users to tweak a multitude of settings to capture their ideal image A new […]
EA and Battlefield Studios have officially launched the third season of Battlefield 6 with its first phase, Warlords: Supremacy, adding three new weapons, new attachments, a Ranked Battle Royale queue for Battlefield REDSEC, and most importantly, the introduction of the Railway to Golmud map. Golmud, which is now the largest map in Battlefield 6, has also helped drive the best spike in the game's concurrent player numbers on Steam in months. Battlefield 6 has struggled in comparison to its numbers at launch. The last time it held a concurrent player count of over 100K players on Steam was in January […]
Conjour is a product marketing expert in a box. Whether it's your first product marketing hire or you're augmenting your team, Conjour helps marketing and sales deliver messaging that converts. You can instantly generate beautiful, on-brand PDF assets, get an AI chatbot trained on your market and messaging, and build a content funnel where strategy and messaging are tied to pipeline.
WiseFi is a deep value investing model that reverses the discounted cash flow to read expectations baked into prices and hunts for mispriced stocks. It compares implied growth and cash flows to current fundamentals, issuing explicit buy and sell signals and Opportunity Scores. The platform publishes every historical pick, win, loss, and backtest since 2016, with free access to data and methodology. Upgrade to Pro for active picks with tickers, full stock pages with signals, and simulated portfolio sleeves.
Micron’s new 9200 MT/s DDR5 RDIMM modules are 40% faster than what’s available today Micron has confirmed that they are sampling 256GB DDR5 Registered Dual In-Line Memory Modules (RDIMM) to customers. These new DDR5 RDIMM modules operate at speeds of up to 9,200 MT/s, which is more than 40% faster than the modules in volume […]
Microsoft is updating the native Windows user interface to create more responsive Windows 11 UI elements through the Windows K2 initiative. The company is transitioning its core Windows 11 elements from third-party frameworks to the Windows-native WinUI 3. In a recent GitHub post by Microsoft engineer Beth Pan, it's clear that Microsoft is making changes even within the WinUI 3 framework itself, demonstrating significant improvements in application launches. The company is using File Explorer and Notepad as benchmarks for performance improvements, as these core apps require much better responsiveness. With the latest set of patches arriving soon, File Explorer will have much less background work to do before launching, meaning that the launch should feel nearly instant.
For example, the latest WinUI 3 patches enable 41% fewer allocations, 63% fewer transient allocations, 45% fewer function calls, and 25% less time spent in the WinUI code powering the framework. This means that the upcoming File Explorer patch should feel noticeably faster with the updated framework, delivering on a promise to make the Windows 11 user interface a much smoother experience. As these changes are expected to be integrated into the WinAppSDK 2.x soon, we should see them arrive in the operating system in the coming weeks. Some changes are still too risky to implement in such a large piece of software, so users will need to wait a bit longer in case the testing encounters issues.
Branch, the office furniture company on a mission to make a great workspace accessible to everyone, today announced a first-of-its-kind collaboration with SEGA: a collection of three ergonomic gaming chairs inspired by the worlds, consoles, and characters that have defined generations of play. The Branch x SEGA Gaming Chair Collection—featuring the Sonic Chair, the Genesis Chair, and the Dreamcast Chair—launches in May 2026 on branchfurniture.com, with prices starting at $569 USD.
These are the first gaming chairs ever launched under the SEGA brand. Each chair builds on the acclaimed Ergonomic Chair Pro platform by Branch, reimagined with subtle, sophisticated design details drawn from SEGA's most beloved properties. Branch's design team translated the visual language of SEGA's most iconic properties into considered details: custom fabrics, textured armrests, branded casters, checkerboard accents, and console-inspired finishes that reward a closer look without overwhelming a room.
Three Amazon employees told The Financial Times that the company's internal AI usage metrics are likely inflated. According to the sources, employees are using MeshClaw, Amazon's internal AI platform, to perform non-essential tasks in an effort to make a stronger impression on managers.
In the letter, which was also shared online, the executive said the board and its independent advisors thoroughly reviewed GameStop's proposal before making a decision.
The firm takes a generalist approach, backing companies across categories such as AI applications, fintech, healthcare, and security. The average check size for this fund will be between $3 million and $5 million, with the aim to back at least 30 startups.
Altman said that Musk's focus on controlling the initial for-profit gave him pause because OpenAI was dedicated to keeping advanced AI out of the hands of a single person, and Altman, with his experience running the prominent startup accelerator Y Combinator, knew "founders who had control usually did not give it up."
The highest amount of unified memory offered on a discounted M5 MacBook Pro was 24GB, but Amazon has a surprise for buyers that’s going to kick you off your feet. At $300 off, you get to be the proud owner of an exceptional configuration, one that offers a whopping 32GB of unified RAM coupled with a 1TB SSD, all for $1,799. Now, is this one of the best deals of 2026 or what? Unfortunately, those wanting the Space Black version of the M5 MacBook Pro will be out of luck, as Amazon’s $300 price reduction is only applied to the Silver […]
Last year, just days before we officially learned that GTA 6 had been delayed to November 2026, developer Rockstar was accused of union-busting with the firing of 34 employees, 31 in the UK, and three in Canada at its Rockstar Toronto studio. Those dismissals spurred an ongoing legal battle between Rockstar and the Independent Workers of Great Britain (IWGB), one that caught the eye of UK parliament and Prime Minister Keir Starmer. Now, British MPs leading the investigation into Rockstar's alleged union-busting have come forward to accuse the company of obstructing legal processes through "silence and closed doors." Per Eurogamer, […]
The shift to TSMC’s 2nm process will make Qualcomm more competitive against Apple, but the biggest drawback is that the company’s chipsets are going to be astronomically expensive. Looking at the Snapdragon 8 Elite Gen 5’s price, which was estimated to cost as much as $280 per unit, a new rumor says that the Snapdragon 8 Elite Gen 6 Pro will kick it up a notch. At $300+, the Snapdragon 8 Elite Gen 6 Pro might only be adopted by ‘Ultra’ flagships, as the high price is expected to reduce adoption amid the ongoing RAM shortage Later this year, Qualcomm […]
As one of the most prevalent operating systems in the world right now, Android continues to receive a lot of limelight, including from its progenitor Google, which has again chosen to dedicate an entire livestream to the OS as a part of its annual I/O event. This year's Android Show has revealed a fair number of goodies that are coming to Android 17 this summer, including Gemini Intelligence, while giving a teaser of the brand-new Googlebook. Here are the choice tidbits from Google's latest Android Show I/O edition Google is now packaging disparate AI services and tools under a single […]
Dead Space is arguably one of the most enduring horror franchises in video games after its run of three games during the seventh console generation catapulted it to a permanent place in the minds of many young gamers between 2007 and 2013. A decade after Dead Space 3 failed to match the success of the first two games, the much-loved 2023 remake of the first game from Motive Studio revitalized hope that we'd see the series make a huge comeback. But that's not going to happen, according to one of the game's original writers and producers, Chuck Beaver. In an […]
Gixo turns notes, topics, or full articles into finished presentation decks within one workspace. You can plan outlines before generation, keep evidence and citations attached, switch among 28 themes after slides exist, and edit content with AI-assisted revisions. Use presenter notes and a timer, share live decks, and export to PDF, HTML, or images without rebuilding in another tool. Teams can draft, review, approve, and deliver from the same deck, moving from first draft to presentation-ready faster.
Google is bringing Gemini into Google Ads dashboards, aiming to make data analysis more interactive, visual and accessible.
What’s happening. Google Ads is rolling out a new Dashboards feature that lets advertisers explore performance data using charts, graphs and tables, powered by Gemini.
Users can customise views simply by typing prompts, with the dashboard updating in real time based on their queries.
Why we care. Data analysis in Google Ads has traditionally required manual setup and navigation across reports.
This update shifts that workflow toward a more conversational model, where advertisers ask questions and get instant visual answers.
Zoom in. Dashboards will display key metrics like impressions, clicks, video views and cost, alongside visual breakdowns of performance across devices, audiences and campaign types.
The goal is to give advertisers a clearer, faster way to understand what’s happening in their accounts.
What to watch. How widely advertisers adopt prompt-based reporting, and whether this reduces reliance on custom-built reports and external analytics tools.
Google Discover has publisher profile pages. They live at profile.google.com/cp/ and appear when someone taps a publisher’s name on a Discover card. These pages aren’t new. They launched in August 2025 with the Follow button rollout, and by November 2025 Google’s documentation referred to them as “source overviews.”
For most of the 47,000+ publishers we monitored, the pages are auto-generated: a name, follower count, social links pulled from the Knowledge Graph, recent posts, and a footer label that reads “Profile generated by Google.”
Since March 2026, though, something changed for a small subset of publishers. A group gained access to enhanced profiles: custom banner images, a configurable links shelf, and the ability to pin posts (labeled “Pinned” in the publisher interface, formerly “Featured Posts”).
They also gained control over the order of their social links, website, and content tabs — something standard profiles don’t allow. On standard profiles, social links are sorted algorithmically by follower count, with the website listed last. On claimed profiles, the publisher decides.
The “Profile generated by Google” label also disappeared entirely, replaced by nothing — a quiet signal that the profile had been claimed.
There’s no public documentation explaining how to get access. No Search Console toggle. No application form. Google appears to have hand-selected participants for what is effectively an invitation-only pilot program.
We identified 54 publishers in this cohort. All are U.S.-based. All publish in English. And what they have — and haven’t — done with the feature over two months of monitoring reveals patterns every publisher should watch before the program scales.
How we found the 54
Our Profile Features Monitor tracks 46,926 publishers across seven languages: English, French, German, Italian, Spanish, Dutch, and Portuguese. To isolate the enhanced cohort, we filtered for publishers that showed persistent enhanced-profile signals across multiple snapshots: active links, full banner headers, or both.
The result: 54 domains with stable access to the enhanced profile surface. The composition of that group offers clues about Google’s intentions:
Tier
Publishers
Examples
National
15
WSJ, Fox News, NY Post, Newsweek, Inquirer
Regional Paper
13
Boston Globe, SFGate, CT Insider, Times Union
Local TV
14
KTLA, PIX11, MyFox8, WSMV, Atlanta News First
Lifestyle Brand
6
Delish, The Dodo, Country Living, House Beautiful
Specialty
6
Pew Research, The Athletic, Gothamist, Civil Beat
The skew toward local news and community publishers is striking and aligns with Google’s public emphasis on supporting local journalism. Nearly half the cohort — 27 of 54 publishers — consists of regional newspapers and local TV stations. National brands are included too, but they’re not the majority.
The two-tier profile system
Under the hood, Google operates two distinct profile architectures. Understanding the difference matters because this isn’t just a cosmetic upgrade. It’s a structural split.
Standard profile (99.9% of publishers):
Auto-generated from public sources.
“Profile generated by Google” label visible.
No publisher control over content or layout.
Claimed profile (the 54 publishers):
No generation label.
Publisher can configure the banner, links shelf, and pinned post.
Publisher controls the order of social links, website, and content tabs (standard profiles sort them by follower count).
This isn’t Search Console verification, structured data markup, or any existing publisher tool. It’s a separate, invitation-only system.
What the 54 publishers actually did
This is where it gets interesting. Access to a feature and its effective use are different. Here’s what the data shows across each configurable surface.
Forty-one of the 54 publishers uploaded a banner image. The remaining 13 have the capability — a “prepared” state — but haven’t used it yet.
What stands out is the production quality. There are no amateur banners in the cohort. Every uploaded image reflects clear professional design investment.
Five distinct visual archetypes emerged:
Brand-pattern: No photography, just the wordmark or abstract identity repeated as a tile. Pure prestige.
Tier predicts archetype. National publishers cluster around brand-pattern banners. Local outlets lean into civic identity and city imagery. Lifestyle brands showcase their content directly.
One anomaly: The Athletic uploaded a solid black square — 656×656 pixels. Whether that reflects deliberate minimalism aligned with The Athletic’s dark UI or simply a broken upload is unclear. It’s the only non-image banner in the cohort.
The format split is revealing: 71% used square banners — likely Google’s recommended ratio — while 29% used wide landscape formats. None used portrait layouts. Based on CDN serving patterns, the minimum recommended resolution appears to be 512 pixels on the longest side.
Publishers that chose wide formats made deliberate design decisions: SecretNYC uses a manifesto-style collage, the New York Post uses a headline grid, and Barron’s uses a geometric pattern. Square appears to be the default safe option.
Links: local TV dominates, nationals ignore it
Thirty-three of the 54 publishers enabled the links feature. Of those, 31 added at least one link, for a total of 65 configured links across the cohort.
The content is overwhelmingly focused on on-site navigation: 85% of links point to the publisher’s own sections, weather pages, live streams, or app downloads. This functions more like a mini site navigation layer than a promotional surface.
The tier gap is enormous:
Local TV: 31 links across 14 hosts (average 2.2 per publisher). Fox affiliates consistently shelve: Watch Live, Weather, Local News, Sub-region, Contact.
National: 9 links across 15 hosts (average 0.6 per publisher). Most nationals didn’t bother.
Three outliers worth noting:
PIX11 published “How to make PIX11 a preferred source on Google,” meta-promoting Discover follows from within the Discover profile itself.
Gothamist funneled donations through `pledge.wnyc.org` with a purpose-specific utm_campaign=discover-profile tag.
Fox Nation placed a direct subscription conversion link (“Subscribe to Fox Nation”) on what most publishers treat as a navigational surface.
Pinned posts (formerly Featured Posts): capability granted, rarely used
Fifty-two of the 54 publishers enabled the Pinned feature. Only 13 currently use it with an active pinned post.
Lifestyle brands were the strongest adopters: five of six had the feature active. Among national publishers, only 2 of 15 used it. The capability exists across nearly the entire cohort. Adoption does not.
About text: Wikipedia out, self-branding in
On standard profiles, the “About” section is auto-generated by Google, usually sourced from Wikipedia. On claimed profiles, publishers write their own.
Within the cohort, 38 of 54 use a custom-written description, while only 16 retain a Wikipedia-sourced version — a surprisingly low number for publishers of this size and prominence.
The tone splits cleanly by publisher tier.
Local TV stations lean promotional (“Your trusted source for breaking news, accurate weather forecasts and local sports across Greensboro…” ).
National and digital-native publishers stay more factual (“Gothamist is a website about New York City news, arts, events and food, brought to you by New York Public Radio”).
One publisher takes a mission-driven approach: Delish — “you don’t have to know how to cook, you just have to love to eat!”
The implication for publishers preparing for this feature: once you claim the profile, you take control of the About section. It becomes your pitch on a Google-owned page.
Notably, the most visible publishers in the cohort chose factual descriptions over promotional copy.
UTM tracking: the blind spot
Only three of the 65 configured links include analytics parameters. Gothamist tagged its donation link with utm_campaign=discover-profile, making it the only publisher in the cohort treating the profile as a measurable acquisition channel.
The Philadelphia Inquirer instrumented two links, but one reused an Instagram bio campaign tag (mktg_acq_ig_organic_bio_offer), meaning Discover traffic from that link will be misattributed to Instagram in analytics.
The other 62 links have no tracking at all. In practice, 95% of the cohort has no way to measure whether profile links generate traffic.
Social platform priorities
On claimed profiles, publishers control the display order of social links and content tabs. Standard profiles don’t: Google sorts links algorithmically by follower count and places the website last. That means the ordering we observe on claimed profiles reflects deliberate editorial choices, not algorithmic defaults:
Local TV stations list Facebook first: 86% (12 of 14). Zero list X/Twitter first.
National publishers spread their bets: Facebook 33%, Instagram 20%, X 20%, YouTube 13%.
Concrete examples: Newsweek places YouTube first and Articles second. Delish leads with Website, followed by Instagram. These are active editorial decisions about which audience channel matters most.
The local TV finding is particularly notable. Despite news media’s historical reliance on X/Twitter, not a single local station in this cohort places it as their primary social link.
Sister-site coordination
For media groups with multiple properties in the cohort, setup patterns reveal whether profile management is centralized or handled locally:
Hearst Connecticut, which has five papers in the cohort, shows near-identical configuration across all profiles. The links structure is the same, including a shared Hearst checkout funnel with publication-specific site IDs. The setup points to a centralized digital team managing profile operations across the group. Even so, each masthead still uses distinct banner art.
Dow Jones, across The Wall Street Journal and jp.wsj.com, uses shared banner artwork: the same wordmark tile, confirmed through perceptual hashing. That points to brand coordination at the asset level.
Everyone else Everyone else — including Fox affiliates, Dotdash Meredith properties, and the Fox News group — shows completely different setups across properties, even within owned-and-operated chains. Profile management appears to be handled locally rather than centrally.
The rollout is still active
Comparing snapshots #9 and #12 — taken 19 days apart — confirms this isn’t a frozen experiment. During that window, four publishers added banners (jp.wsj.com, New York Post, SecretNYC, and Everyday Health), one activated Links for the first time (New York Post), and jp.wsj.com (The Wall Street Journal’s Japanese edition) entered the cohort entirely.
No publishers lost features. The program is still expanding within the cohort, and new participants continue to appear.
The adoption paradox
We scored each publisher on a composite 0–6 scale, assigning one point for each of the following:
Banner uploaded
Links feature active
Featured Posts active
At least one configured link
Four or more social platforms listed
Any UTM tracking present
Nobody scored 6. The distribution:
Score
Publishers
%
2
22
41%
3
10
19%
4
14
26%
5
8
15%
6
0
0%
National publishers with the largest audiences are the least engaged with the configurable surface, with a mean score of 2.93. Most uploaded a banner and stopped there.
Local TV stations — despite having the smallest Discover footprints — are the most engaged, with a mean score of 3.57. Lifestyle brands score highest overall at 3.83, yet their Discover visibility trajectory is the flattest in the cohort.
And here’s the critical finding: feature adoption shows no correlation with visibility trajectory.
Across the cohort, the 180-day late/early capture ratio ranges from 0.23x for Prevention — down 77% — to 4.27x for NewsNation — up 327%. Variance is massive within every tier.
KTLA scores high on adoption, with seven links, a full banner, and active profile engagement, and grew 3.69x. But Delish also scores high and declined to 0.90x. MyFox8 configured five links and fell to 0.52x.
Publishers that fully utilized the configurable surface show no better visibility trajectory than those who used it minimally.
This feature gives publishers a controlled surface for branding and navigation, not a ranking lever. It’s a profile page, not an algorithm input.
What this means for publishers
The program is U.S.-only and invitation-only for now. Across the six other language markets we monitor — French, German, Italian, Spanish, Dutch, and Portuguese — we found zero enhanced profile deployments: not a single banner or configured link outside the English-language cohort.
But the underlying infrastructure is already in place. All 47,000+ publishers we track already have profile pages with follower counts, social links, and content feeds. The enhanced features sit on top of that existing architecture. Google isn’t rebuilding the system. It’s selectively unlocking capabilities within it.
If — or when — Google scales this, here’s how publishers should prepare:
Audit your structured data now. Profile social links are pulled from your sameAs/JSON-LD markup. Errors there will carry over to your profile. Verify what Google will display before you’re given control.
Design a banner. Use a square format (1:1 ratio) with a minimum resolution of 512px, and treat it as a professional brand asset. The 54 publishers in this cohort set a clear standard: there were no amateur images. Think about which archetype fits your brand: a wordmark tile for prestige brands, local landmarks for regional publishers, or content-driven imagery for vertical and lifestyle outlets.
Plan your link strategy. The data suggests that section navigation and utility content — weather, live streams, and similar recurring destinations — drive the most engagement. Local TV stations treating the profile as a mini site navigation layer are the clearest power users. Decide now which five to seven links represent your most valuable entry points.
Instrument from day one. Almost nobody in the current cohort tracks profile link performance. Adding a dedicated UTM campaign parameter — utm_campaign=discover-profile, for example — would put you ahead of 95% of the pilot group on attribution alone.
If you’re a media group, decide your operating model. Should profile management be centralized or handled newsroom by newsroom? The cohort shows both models. Hearst Connecticut runs one coordinated setup across five papers, while Fox affiliates manage profiles independently at the station level. The important part is that the choice is deliberate — not something decided accidentally when individual newsrooms start receiving invitations.
Methodology
Data comes from the 1492.vision Profile Features Monitor, which tracks roughly 47,000 publishers across seven languages through recurring snapshots of profile metadata. The 54-publisher cohort was identified through persistent enhanced-feature signals observed across multiple snapshots between March and May 2026.
Visibility trajectories are based on proprietary capture data. All findings are descriptive only: the cohort reflects Google’s selection criteria, not a random sample, and this dataset does not support causal claims about feature impact.
The full analysis — including the complete 10-phase timeline, banner image gallery, snapshot-by-snapshot evolution, and tier-by-tier breakdowns — is available at 1492.vision/research/discover-publisher-profiles-en.
Exim has released security updates to address a severe security issue affecting certain configurations that could enable memory corruption and potential code execution.
Exim is an open-source Mail Transfer Agent (MTA) designed for Unix-like systems to receive, route, and deliver email.
The vulnerability, tracked as CVE-2026-45185, aka Dead.Letter, has been described as a use-after-free
Forza Horizon 6 runs fast on RTX 50-series PCs Alongside their GeForce 596.49 “Game Ready” driver, Nvidia has released official benchmarks for Playground Games’ Forza Horizon 6. At launch, Forza Horizon 6 will support ray tracing on PC alongside Nvidia’s DLSS 4.5 Super Resolution technology and Multi Frame Generation (up to 4x). Nvidia has confirmed […]
Microsoft is standardizing Copilot access across Windows, Mac, and Web by replacing varied app triggers with a single floating UI and the Alt + C shortcut.
Dead Space is arguably one of the most iconic and recognizable franchises in gaming, even if it has been 13 years since the last instalment in the sci-fi space horror shooter series. Now, in a recent interview with FRVR, Dead Space writer and producer, Chuck Beaver, has explained why the chances of Dead Space 4 happening are vanishingly thin in the current gaming landscape. Unfortunately for fans of the genre, it seems as though a combination of factors is at play, but the majority of the blame appears to lie on poor sales figures, especially compared to the modern video game industry's expectations.
Beaver explains that a game with the production value of Dead Space—a AAA horror with high production value—would need to sell incredibly well in order to cover the development costs: "Horror games have a bit of a ceiling, you know, and I think the number back in Frank Gibeau's day was 5 million units to keep going on Dead Space. I think the number is like 15 million units now, given the cost of things." Meanwhile, when Resident Evil: Requiem recently crossed 6 million sales in just over two weeks, it became the fastest-selling Resident Evil game to date. He goes on to comment that "companies now are looking for the next Fortnite. They need something that is a perennial moneymaker…something like a single-player package game with no live-service offering that's like it's just a dinosaur fossil of a business model."
Global semiconductor materials market revenue increased 6.8% year-over-year to $73.2 billion in 2025, SEMI, reported today in its Materials Market Data Subscription (MMDS). Growth was supported by gains in both the wafer fab materials and packaging materials segments, reflecting higher process complexity, advanced-node demand, and continued investment in high-performance computing and high-bandwidth memory manufacturing.
Wafer fabrication materials revenue increased 5.4% to $45.8 billion. Lithography-related materials, including photomask, photoresist and ancillaries, along with wet chemicals, posted strong double-digit growth as higher process intensity and tighter lithography requirements continued to increase materials consumption.
TSMC has allocated an additional $20 billion to expand its facility in Phoenix, Arizona, at the Fab 21 site. According to the latest TSMC board resolution meeting, TSMC Arizona, a subsidiary of TSMC, will receive up to $20 billion for now, with the possibility of further capital injections in the future. This resolution supports the expansion of TSMC's Fab 21 site with additional land purchases, expensive EUV equipment, and more semiconductor manufacturing tools. The company has already invested about $65 billion in ongoing Arizona projects and pledged an additional $100 billion in capital expenditure on top of that. The total TSMC Arizona capital expenditure is projected to reach $165 billion, with parts of the additional $100 billion package being gradually unlocked, as seen in today's board meeting resolution.
Interestingly, TSMC Arizona reportedly generated about $514 million in profit last year, its first year of operations. Given TSMC's gross margins of about 66%, this suggests that Fab 21 generated approximately $1.5 billion in revenue. TSMC does not explicitly separate revenue streams from each fab publicly, but these numbers are impressive considering the fab has only been operational for a year. Typically, a fab's first-year performance is not this strong, but it seems TSMC remains an industry leader in this area as well.
Since the January 2024 Early Access release of Palworld, Pocketpair, the developer and publisher behind the open-world creature collector, has been growing its Pal-flavored empire, announcing a life sim, Palworld: Palfarm, Palworld Mobile, a Palworld TCG, and even a dating sim, "Pal♡world! More Than Just Pals." Now, according to recent trademark filings at the US PTO, it looks as though Pocketpair is planning to release something called "Palworld Online," although there's not all that much in the trademark filing to go by otherwise. The trademark is filed under IC9, covering digital and physical goods with specific mention of game cartridges and downloadable media; IC41, likely to cover online gaming services and related musical IP; and IC42, which covers, among other things, design and development of computer hardware and software.
Since Palworld already has online gameplay as central to the experience, and the studio is already involved in a handful of other genres within the same IP, online speculation about the trademark is leaning in two directions: a gacha game or a more traditional MMO experience. While either seems equally likely at this point, the recent trend for game studios to lean into gacha mechanics as a money-making mechanism has fans of Palworld concerned about the future of the franchise. It should also be mentioned that the trademark application also includes specific mention of "artificial intelligence as a service" and "services featuring software using artificial intelligence (AI) for developing computer games," which could simply mean traditional AI, as in the kind that powers player interactions with in-game enemies, but the inclusion of the acronym AIAAS suggests that there will be some sort of AI integration in whatever Palworld Online becomes.
"Any sale or transfer of Anthropic stock, or any interest in Anthropic stock, offered by these firms is void and will not be recognized on our books and records," the company's support page reads.
Google and SpaceX are in talks to build data centers in orbit, pitching space as the future home for AI compute, even as costs today remain far higher than on the ground.
Google unveiled its new AI-first Googlebooks laptops, more agentic Gemini features, vibe-coded Android widgets, Gemini in Chrome, refreshed Android Auto, and more ahead of I/O.
Anthropic's new tools are designed to help law firms automate specific clerical functions — things like document search and review, case law resources, deposition prep, document drafting, and other related areas.
The company says Googlebooks, which are launching this fall, are the first laptops designed from the ground up for Gemini Intelligence to offer personal and proactive help.
To create a widget, users will be able to describe what they want using natural language. For example, you could ask the feature to "suggest three high-protein meal prep recipes every week" in order to get a custom dashboard that you can add and resize on your home screen.
Intrusion Logging is a new part of Android’s Advanced Protection Mode, which aims to help protect human rights activists, journalists, and dissidents from government spyware attack and law enforcement forensic devices.
Community Bank, which operates in Pennsylvania, Ohio, and West Virginia, disclosed a cybersecurity incident that exposed customers’ names, dates of birth, and Social Security numbers.
The feature is designed to help people get real-time context about trends and breaking stories, as well as receive recommendations, all within conversations.
During a recent earnings call for the fourth quarter of fiscal year 2026, Arm executives shared some interesting insights into the company's outlook on the future of computing devices. According to CEO Rene Haas, CPUs will eventually surpass GPUs in terms of total compute cores. And yes, you guessed it:...
Inspired by the early days of CCleaner, FluentCleaner is a cleanup utility that focuses on removing temporary files, browser cache, logs, and leftover clutter without aggressive registry cleaning or scareware tactics. The app also supports community-maintained cleaning databases and optional extensions.
Lipa filed the lawsuit in California on May 8. It alleges Samsung prominently displayed a photograph of her face on television models sold in the US without "her knowledge, without consideration, and as to which she had no say, control, or input whatsoever."
Micron has started to ship its fastest DDR5 RDIMM memory modules, which feature 256 GB capacities & up to 9200 MT/s speeds. Micron Offers 40% Boost Vs Current "In-Volume" DDR5 RDIMM Memory Modules, Brings 256 GB Capacities With 9200 MT/s Speeds As Agentic AI requirements grow, memory makers are rolling out faster and higher-capacity memory kits to meet the demands of AI firms. JEDEC is also pushing the DDR5 MRDIMM standard up to 12,800 MT/s, and today, Micron has announced that it is sampling its 256 GB DDR5 RDIMM modules with up to 9200 MT/s speeds. The main highlights include: […]
If you were asked to name some highlight announcements from The Game Awards 2025, you might call out reveals like Larian's new Divinity game, ACE Combat 8, or Mega Man: Dual Override. But what was arguably the biggest reveal of the night, was Star Wars: Fate of The Old Republic, a new single-player RPG from former BioWare developers and legendary director Casey Hudson. Though we still have a long time to wait before we can play the game ourselves, a new report from Bloomberg revealed a few new details around how the game came to be, and what we can […]
Google has a new laptop platform coming out called the "Googlebook" and it's meant to replace or succeed Chromebook. It's powered by Android and "designed for Gemini Intelligence." The main highlight is native integration with other Android devices and a "Glowbar" that dynamically reacts to what your Googlebook is doing.
SwiftDesign CRM unifies client management, sales pipelines, and documents in one clean workspace. Track pipeline value, forecast revenue, and visualize deals on Kanban boards. Share secure client portals with magic links for uploads, folders, and native chat. Create rich client profiles, manage spreadsheets and text docs, and send invoices without switching tools. Use private or team boards, monitor top clients with real-time dashboards, and get started fast with a generous free plan.
Morph lets teams build rule-based data workflows without code. Connect Xero, CSV extracts, and turn messy files into structured outputs in minutes that work for you. Run workflows on schedules, process thousands of rows in real time, and keep data private—data never persists on servers and is discarded on delivery.
Android Auto and cars with Google built-in are getting upgrades. Drivers can look forward to a rich new experience, premium entertainment and a more capable Gemini.
Google has confirmed a bug with the Discover report within Google Search Console. Google had a data “logging” error that caused a decrease in clicks and impressions for the Discover report between the dates of May 7, 2026 until May 8, 2026.
Google said this is just a “data logging only” and your positioning in Google Discover was not impacted.
The issue. Google again said a data logging issue caused reporting issues with the Discover report between May 7, 2026, and May 8, 2026.
This may have resulted in a “decrease in clicks and impressions in the Discover performance report,” Google posted.
Why we care. There were a number of publishers noticing a drop in clicks and impressions based on this report, keep in mind, if you do also, it is likely related to this reporting bug.
Annotate your reporting and update your stakeholders that May 7 – May 8 data for Discover was broken and should be disregarded.
RubyGems, the standard package manager for the Ruby programming language, has temporarily paused account sign ups following what has been described as a "major malicious attack."
"We're dealing with a major malicious attack on RubyGems right now," Maciej Mensfeld, senior product manager for software supply chain security at Mend.io, said in a post on X. "Signups are paused for the time being.
Nvidia’s ready for the newest PC game releases with its GeForce 596.49 “Game Ready” drivers. Nvidia has officially released its GeForce 596.49 “Game Ready” GPU drivers. This driver is Nvidia GeForce “Game Ready” for Forza Horizon 6, Directive 8020, and Subnautica 2, some of this month’s biggest PC game releases. Nvidia has also confirmed that […]
With its iconic compact design, versatile Leica zoom lens, plus Panasonic's latest sensor and processor — the Lumix L10 has all the ingredients to be a hit
The more interactions an AI model has, the less reliable it becomes, experts find, as even the best only scored 80.9% – and the worst scoring just 10.0%.
Fatal Fury publisher and Neo Geo arcade system creator SNK has announced its investment in a newly established game development studio founded by Tekken creator Katsuhiro Harada.
PlayStation 4 users who have wishlisted Grand Theft Auto 6 have started receiving messages urging them to upgrade to a PlayStation 5, suggesting marketing for the game has officially begun.
As bad actors weaponize AI to exploit software vulnerabilities at unprecedented speed, companies are increasingly recognizing the need to bolster their cybersecurity defenses. The round valued the three-year-old startup at $725 million.
Google is preparing to refresh its laptop lineup, replacing the traditional Chromebook branding with the new "Googlebook" name. According to a now-deleted XDA Developers post, archived by some Redditors, Google is collaborating with several PC OEMs to launch what seems to be the successor to its well-known Chromebook devices. Notably, Acer, ASUS, Dell, HP, and Lenovo will be participating in the launch of the new Googlebook lineup, with devices reportedly coming this fall. Each of these OEM partners will create their own version of the Googlebook, adding their unique style. We have seen an official render featuring what appears to be a glowing RGB strip, which the company calls "Glowbar." Whether it will be more than just a gimmick remains to be seen.
The focus of Google's customization with these Googlebooks is the deep integration of the company's AI services. These include applications such as "Magic Pointer," which takes context from the user's screen and uses Gemini AI to understand the situation, providing additional context or using an image generation mode to combine and edit photos. Another highlighted feature is "Cast My Apps," which connects Android smartphones and allows users to interact directly with their phones from the laptop. This is similar to Apple's macOS iPhone Mirroring app, indicating that Google is taking inspiration from other ecosystems. Interestingly, we still don't know what hardware these laptops will run on, but we expect more details to be revealed at today's Android Show I/O Edition or in the coming weeks.
The update came via Tan's latest post on X, in which he congratulated Nvidia CEO Jensen Huang on receiving an Honorary Doctorate in Science and Technology from Carnegie Mellon University for his contributions to accelerated computing and AI. Huang chose to receive the award from Tan, who posted photos from...
Porsche's approach is less about chasing extremes and more about refining every variable that affects lap performance. Manthey Racing – best known for its work on Nürburgring-dominating 911 variants – applied a familiar formula to the Taycan: incremental improvements across software, aerodynamics, and chassis hardware.
The company will showcase its newest liquid-cooled memory kit at the Computex 2026 event. Origin Code Announces Vortex 48 GB DDR5-6200 CL28 Kit, Coupled With a LCD-Equippd Water Block for Enthusiast-Grade Cooling Memory maker Origin Code has expanded its Vortex memory lineup by introducing a new 48 GB memory kit, featuring two 24 GB memory sticks rated at 6200 MT/s. At just CL28, reaching 6200 MT/s is exemplary, but thanks to the exceptional design, the Vortex 48 GB (2x 24 GB) DDR5 kit is able to reach new heights without compromising on the latency. Moreover, the kit can hit 8000 […]
NVIDIA is reaching for the stars, literally, as the company plans to build its future AI datacenters in outer space as terrestrial resources become a major constraint. Our Planet Might Not Be Able To Sustain Future AI Datacenter Demands. That's Why NVIDIA Is Looking Into Space As The Next Horizon For AI Chips Outer Space is becoming the new real estate gold mine for AI datacenters. Building data centers in space can be costly, but as commercial spaceships such as SpaceX's Starship and Falcon Heavy become viable, companies are seeing outer space as the new frontier to scale out their […]
There's no time like the present to become the proud owner of a wicked-fast gaming laptop, especially when the memory shortage will keep affordable PC hardware out of reach for a couple of years. On this occasion, MSI’s Vector 16 HX AI continues to be our pick for the best ‘price to performance’ machine because not only is this portable powerhouse equipped with an RTX 5070 Ti with 12GB of GDDR7 VRAM, but it’s also listed on Amazon at $220 off, making it one of the biggest discounts that we’ve seen to date, with its current price listed at $1,580. The PRAGMATA […]
It's a fundamental trade-off for Apple: people use their iPhones quite a lot during summers, when a dual OLED-based brighter screen comes fairly handy, but at the cost of turning your phone into a thermal brick. Now, one tipster believes Apple will leave this conundrum to another day, and that the iPhone 18 Pro and Pro Max will "definitely" miss out on a dual OLED screen. The iPhone 18 Pro won't feature a noticeably brighter display unless Apple revamps its thermal management strategy, and pairs it with a bigger battery The famous Weibo-based tipster, Digital Chat Station, has just declared […]
SEGA just published its fiscal year 2026 full-year financials, and while some Japanese publishers like Capcom can't seem to miss lately, that's not the story for SEGA. This past year was not a gangbusters year for SEGA on the commercial side, despite putting out some excellent games like SHINOBI: Art of Vengeance and Persona 3 Reload. The company reported a significant $31.6M net loss and saw a live service game based on its flagship franchise, Sonic Rumble Party, perform far weaker than expected. But that's where all of this could be a good thing for players. If you lost over […]
Today, Pearl Abyss has reported a transformative quarter, with the launch of its long-awaited open world action RPG Crimson Desert turning in excellent sales numbers and setting the Korean developer on course for what could be its most profitable year on record. Crimson Desert launched on March 19, 2026 and immediately made a statement by topping Steam's Top Sellers chart across major markets despite being an entirely new IP. Despite the lack of overwhelmingly positive critical reviews, its sales trajectory was relentless: Pearl Abyss reports that the split between PC and console was nearly even at 50:50, which is notable for […]
Tekken series creator Katsuhiro Harada left Bandai Namco, and thus the franchise, at the end of 2025, but the legendary game developer is returning quickly to the industry with VS Studio, a brand-new game development studio created with investment from SNK Corporation. Established on May 1, SNK will support its launch and plans to make it a consolidated subsidiary. "The new studio and SNK will collaborate on game software development to further strengthen their development capabilities," the announcement press release says. "We are pleased to announce the launch of our new game development studio, VS Studio. VS Studio's philosophy is […]
Antec has dropped new cases that bring the panoramic view to the next level with triple-sided tempered glass panels. Antec Launches C6 Curve Air Cases With Three-Side Tempered Glass Panels in Three Flavors, Offering Incredible Panoramic Views The Antec C6 Curve Air might be the only case with such a unique design, but it looks gorgeous. The company has just announced the C6 Curve Air series cases that bring the panoramic view to the next level. By deploying a curved tempered glass panel at the front, the C6 Curve Air brings a unique view that is distinguished, but compromises the […]
As CPU demand continues to rise on the AI hyperscaler front due to Agentic workflows, NVIDIA is seeing massive demand for its Vera CPU racks with several major customers lining up as early adopters. China's Alibaba Among The List of Early Adopters For NVIDIA's Agentic-AI Focused Vera CPU Racks Some major names have emerged for NVIDIA's upcoming Vera CPUs, which will usher in a new era of performance and efficiency at scale in AI. The Vera CPU, accompanied by the Groq 3 LPX "LPU," has tremendous potential for Agentic AI workflows, and this has led AI firms to secure early […]
A Financial Times report claims the Trump administration is considering restrictions on Chinese cellular modules as the FCC escalates its crackdown on Chinese communications technology, potentially affecting massive portions of the global IoT and electronics supply chain.
TSMC's Fab 21 becomes profitable in the first year of operations, though TSMC continues to struggle with labor shortage, water shortage, and is concerned about the long-term power supply. Nevertheless, it allocates $20 billion on further development of the project.
After a new "low Latency Profile" for Windows 11 was discovered last week, the community has responded severely, criticizing Microsoft for suppressing a bigger issue. The company, however, is defending the decision on social media, saying that it's only doing what every other operating system already does.
Outhentik helps local businesses collect video reviews privately before they appear on Google. Customers scan a QR code, record a short video and star rating in the browser, and you receive it first. Approve the best to publish as testimonials or encourage happy customers to post on Google while handling complaints privately to protect ratings. It offers real-time alerts, custom branding, per-location routing, a reputation dashboard, and easy downloads and embeds to help turn genuine clips into trust and prevent bad reviews from going public.
Won is the gate that pays for everything: the click happens, the recommendation lands, and the agent transacts.
Won has changed beyond recognition in the last 24 months. It used to mean a click on a search result, the human doing the picking, the brand competing for attention against nine blue links. It still means that, sometimes.
It can also mean an assistive engine naming your brand to a user who accepts the recommendation. Or it can mean an Agent transacting on the user’s behalf.
All of this is about delegation: how much we delegate to machines, and when. Delegation in the context of search and AI is far from new. We’ve delegated “finding the books to the librarian” since AltaVista.
What’s new is that the boundary of what and where we delegate is now flexible: the user can hand more of the journey to the engine than ever before, and the brand that wants to win has to be ready for every option on the delegation spectrum.
What hasn’t changed: The point of search
Underneath the three mechanisms sits the same commercial truth that’s been the point of search since Sergey Brin first articulated it: get the user to the best solution to their problem as efficiently as possible.
AI hasn’t changed the point of search. AI assistive engines and agents simply get the user to the best solution to their problem significantly more efficiently than search: a 15-minute purchase journey through ChatGPT that would have taken a week through traditional Search. In essence, AI removes an enormous amount of friction inherent in search.
The delegation boundary is the line between what the user does for themselves and what they hand to the engine. The further the user pushes it toward the engine, the less work the user does, and the faster won arrives. The further the user holds it back, the longer won takes.
From problem to purchase in 15 minutes with ChatGPT
I’m a double bass player, and I have a huge bass amp in my living room. I also have a guitar my father gave me when I was 18, which I’ve never played much, because I became a professional double bass player in the 1990s, so the guitar has lived as a keepsake for most of its life.
A few months back, I got an offer to play a solo gig at the jazz club opposite my flat. I had a guitar, but no guitar amp, and I didn’t want to buy a guitar amp for one gig. I figured I could just use the bass amp.
Here’s my conversation with ChatGPT:
Me: Can I play guitar through my bass amp? Will I break it?
ChatGPT: No, you won’t break it. But it’ll sound terrible.
Me: How do I make it sound good?
ChatGPT: Three pedals: reverb, compression, equalization.
Me: Which ones?
ChatGPT: Boss, JHS, TC Electronic.
Me: Price?
ChatGPT: Around $250 for the set.
Me: Cheaper. I’m more of a singer than guitarist.
ChatGPT: I can get you there for $125.
Me: I need delivery by Friday, guaranteed. Saturday gig.
ChatGPT: Thomann in Europe, Sweetwater in the US. Both will hit Friday.
Me: Europe.
ChatGPT:[Thomann link]
Me: Clicks. Buys.
The Google team specifically asked me to make this point in the keynote, and I want to land it here too because they care about it for a reason most marketers haven’t worked out yet.
The engine made decisions for me all the way down the funnel. It decided whether the question even had an answer, which pedals were worth shortlisting at which price tier, and who could meet a Friday deadline.
My delegation boundary sat at the perfect click. ChatGPT owned the entire research-and-recommendation funnel. I owned the buy button, and only because Thomann doesn’t yet have an agential checkout. If they had, the agent would have transacted while I was making coffee.
The point isn’t that the funnel compressed from a week to fifteen minutes. The point is what happened inside the compression: the engine made dozens of small decisions on my behalf, each one quietly closing off options that might otherwise have stayed open.
A different engine might have surfaced different brands, recommended a different price tier, or picked a different supplier. The brand that wins isn’t the one the user chose. It’s the one that survived every one of those upstream decisions the engine made before the user ever saw a recommendation.
Two things put my boundary that far to the right.
Emotional weight: The pedals just needed to be good enough, not perfect.
Domain expertise: I’m not a guitarist. I have no opinions about boutique pedal brands. The comparison work a serious guitarist would relish is friction I’d happily have someone else do.
A working professional would have approached the same purchase entirely differently. A studio musician whose tone is their living would have gone into the shop, plugged the pedals in, and decided in the room. A geeky enthusiast would have spent the week on Reverb forums comparing JHS to Strymon to Walrus, because for them, the research is the fun, the comparing is the point.
The point here is that you have the same purchase made by three buyer personas, each with a completely different position on the delegation boundary, and Thomann needs to be ready to win all three.
I’ve bought over €2,000 of equipment from Thomann since.
The single-mode assumption is dead, three modes coexist now
For two decades, “optimize for search” was the whole of the job: get in the top 10 and win the click at each stage of the funnel. Exhausting work, and it’s no longer enough.
That single approach has been replaced with three modes running in parallel. Search hasn’t gone anywhere. It just has assistive and agential sitting alongside as alternatives for all or part of the journey for each use.
Search tolerates a fuzzy or unclear brand because the human will do the sorting.
Assistive tolerates less of it, because the AI is recommending you to the user, and the AI’s credibility is on the line every time it uses your name.
Agent tolerates none of it, because the agent transacts without asking, and a fuzzy brand is exactly the kind of risk the agent will quietly route around, and the user will never know.
Won looks different in each mode.
In search, won is the click, and then the user finishes the journey on your site, and you need to deal with friction (objections, questions, and clarifications).
In assistive, won is the AI engine naming you and the user accepting the name without further verification, and so most of the friction has already been dealt with.
In agent, won is the transaction completed without anyone consulting the user, friction reduced to zero from the user’s point of view.
The pedal-buying journey sat at the assistive end, and could have been at the agential end. The professional studio musician sits at the search end. The geeky enthusiast sits at the search end too, because for him, the friction is the entertainment.
The delegation boundary moves with every purchase, person, and culture
A user might delegate a coffee order to an agent without thinking, ask an assistive engine for advice on a kitchen renovation but make the final supplier call themselves, then spend an hour happily window-shopping for a bracelet that’s “just what I always wanted.” Same person, same week, three positions on the boundary, and all three engines doing useful work.
The diagram shows that one person sets the delegation boundary at completely different positions depending on the purchase. A wedding venue lives at the far left of search mode, because the decision is emotional and irreversible, and you wouldn’t want AI to make that journey for you.
A few notches to the right, still in search mode, you’ve got someone who’s a sock collector and is window-shopping the listings because the choosing is the point. Further right, still in search mode but inching toward assistive, you’ve got the strategic business contract where only the human holds the strategic context that the AI doesn’t have access to.
Cross over into assistive mode, and you’ve got the holiday I’m planning, where I’m asking the AI for advice but cross-checking through search to challenge the results before I commit. A notch further right, still inside assistive mode, you’ve got the kitchen renovation where I’m taking the AI’s advice on what’s possible, but I’m picking the supplier myself, because the supplier relationship is one I’m going to live with for years.
Cross again into agent mode, and you’ve got the holiday I already know: the agent books the cheapest familiar hotel without consulting me, because I’ve stayed there before and it’ll be fine.
Further right, the pragmatic sock purchase where I just need the right pair in the right size by Tuesday, and the brand doesn’t matter a great deal. And right at the far end, the taxi from A to B, where I genuinely don’t think about it, the agent picks the ride, the agent pays, and I get to my destination with zero fuss or thought.
Same person, eight different positions on the boundary. The variability is the whole AAO game: you have to have a strategy that will win the click at every stage across the Delegation Boundary. The boundary tracks risk, human preference, emotional weight, reversibility, and a half-dozen other things.
You have to wrap that into your strategy on top of the cascading confidence, the 10 gates, the entity home, the push-layer entry modes, the framing gap, and the funnel flip this series has been piling up since February 2026.
7 factors tell you where the delegation boundary sits in your category
Score yourself against seven broad factors (and add your own, if you like):
Emotional weight: The more the purchase touches identity, family, or values, the harder to delegate.
Domain expertise required: The more specialized the decision, the more users either delegate fully (because they know they don’t know) or refuse to delegate (because they think they do).
Price relative to income: A $2 coffee delegates easily, a $20,000 car doesn’t.
Purchase frequency: Habitual purchases delegate readily, one-offs need scrutiny.
Regulatory context: Financial, medical, and legal categories carry compliance constraints.
Cultural context: Trust in agents varies by market and demographic.
Evaluate your category and you get a credible read of where your audience sits, how much friction they’re willing to hand to the engine, and where you need to focus your work. You’ve also done something less obvious, but even more important than scoring: you’ve grouped your audience by behavior at the decision moment rather than by demographic or category labels.
For two decades, we built paid and organic strategies based on how humans see the world: by category, by demographic, by geography. In Google Ads, five-star hotels in Bali went in one ad group, hostels in Bali in another, and five-star hotels in Thailand in a third, because that’s how a marketer thinks.
With AI, the engines stopped thinking that way. For Performance Max and AI Max, you absolutely must group by intent to get performance. Five-star hotels in Bali sit in the same cohort as five-star hotels in Thailand, because the intent (luxury accommodation) holds the cohort, and the geography doesn’t.
Gemini thinks in intent cohorts, not human categories, and the same lesson applies across Organic, ChatGPT, Claude, and other LLMs.
What matters here: AI groups by intent, AI builds the cohorts, and the brand optimizing against the old human structure is competing in categories the engines have left behind.
For years, Google representatives have told us that SEO (or assistive agent optimization, the newer discipline that extends SEO to cover assistive engines and agents) is all about intent, and the point they perhaps didn’t make clear enough is: that’s because it’s how AI thinks.
The user delegates, the engine commits
Here’s the point most brands haven’t seen yet: the user and the engine work in tandem, and your strategy needs to account for that.
Nothing happens without the user’s mandate. The agent doesn’t take over because the assistive engine has decided it’s time. The user pushes the boundary by handing the engine a mandate, and the engine acts within that mandate. The delegation boundary isn’t drifting toward the engine on its own: it is being intentionally moved by the user on a case-by-case basis.
Every engine has been delegated to, and delegation forces commitment. We hand search the job of finding the 10 best links for our query, and Search has to commit to which 10. We hand the assistive engine the job of recommending one brand from a comparison set, and it has to commit to which one. We hand the agent the job of executing the transaction, and it has to commit to which transaction.
Different layers of delegation, different consequences when the commitment is wrong, but the act of commitment is universal across the delegation spectrum, because every engine has been handed a job that ends in an answer (even if that answer is giving us a choice of 10).
The algorithms learn at three levels, and they learn differently across the three engines (search, assistive, and agential):
Individual level: What this specific user has accepted, overridden, ignored, repeated. The narrowest scale, fully personalized. Heaviest in Agent mode (where the agent acts on this specific user’s behalf), significant in Assistive mode, negligible in Search.
Cohort level: What users with this combination of intent signals have accepted on average across thousands of comparable journeys. Wider than the individual, narrower than everyone. Decisive in Assistive mode (the engine needs to know “what works for users like this one”), important in Agent mode as a fallback when individual signal is sparse, lighter in Search.
Global level: What the algorithmic trinity has encoded about the brand from the world’s record. Not user behavior but encoded knowledge, stored in three places simultaneously: the LLM as parameters baked into model weights during training, the search engine as the indexed corpus and ranking signals, and the knowledge graph as entity nodes, relationships, and attributes. Three storage layers, three update cadences, three signal types, all encoding the same fundamental thing: what the AI has come to believe about the brand from everything brands publish and everything others say about them.
Three concentric circles. The user at the center. The cohort around the user. The global world around the cohort. The first two layers are about behavior: what users do with you.
The third layer is about knowledge: what the algorithmic trinity has encoded about you across LLM parameters, search index, and knowledge graph.
The brand has direct leverage at the third layer (everything you publish, everything written about you, everything that becomes part of the corpus the trinity reads from) and indirect leverage at the first two (through the experiences that shape what users do).
Important: The third level is the one that compounds the longest. Every won event Thomann has earned across every customer in every cohort over the last 28 years isn’t just training the cohort signal: it’s feeding the global priors that every future model trained on widely available data will inherit.
Brand confidence work done today (and every “today” past and present) compounds into future models on substrates the brand never directly trains. That’s the deeper structural reason systematic effort compounds in the AI era. Train the substrate, not just the signal.
Why the cohort signal isn’t destiny, and where your opportunity lies
If the engines weighted what they had already learned as the only voices that mattered, no challenger brand could ever break in.
The dominant brands would dominate forever, the individual histories, the cohort patterns, and the global priors would lock in, and AAO would be a closed game where only the incumbents win.
Luckily, that isn’t the reality. What the engine has already learned is heavy, but it isn’t absolute. The brand that establishes a stronger claim than the brands the engine recommends and advocates for can break in, and the layers the brand can move are cohort and global. (The individual layer can be influenced through other communications channels, but is effectively closed in the AI engines because they are increasingly walled gardens.)
The route in is to claim, frame, and prove. Make your claim, frame the claim, and prove it with evidence across enough sources that the engine has the corroboration to move you up.
Underneath that work sits the understandability, credibility, and deliverability process:
Understandability built through clear knowledge of who you are and what you do.
Credibility built through N-E-E-A-T-T.
Deliverability built through topical ownership.
Get all three. Once your confidence clears the threshold:
The cohort signal that currently favors your competitor stops being the only voice the engine hears.
The global layer starts absorbing your contribution alongside the incumbents’.
Your claim becomes framed and proved in a way the engine can resolve and prioritize.
That’s the only way an outsider gets in. It’s also the route every dominant brand took to become dominant in the first place.
What wins at won is confidence
When push comes to shove, what decides the outcome at won is the confidence the algorithm has in your brand at the moment of decision.
Confidence at the moment of:
Ranking in search.
Recommending in assistive.
Action in agent.
The mode, channel, and cohort change, but the question doesn’t.
Content and context are table stakes today. Content is what you’ve published, where, in what structure: every brand doing digital marketing seriously has been doing it for years, since Bill Gates wrote “Content is king” in 1996.
Context is the match between your content and the user’s intent at the moment they’re asking. Both are table stakes, so neither differentiates at the recruitment, grounding, display, and won gates.
Confidence is what’s left, and confidence is what we can measure at the bottom of the funnel. Three things, you measure at the bottom of the funnel brand results (the due diligence rabbit hole):
You measure the accuracy of the results about your brand.
You measure the positive sentiment in the results about your brand.
You measure the consistency of the results about your brand across all of the engines.
How right, how positive, how consistent: that is your measurement of confidence across the AI spectrum.
This is exactly where Thomann won my pedal purchase. ChatGPT was confident enough in Thomann’s information to commit to a Friday delivery on Thomann’s behalf, on a Tuesday, with my Saturday gig riding on it.
Hundreds of European suppliers could, in theory, have gotten those pedals to me by Friday. ChatGPT picked Thomann because they had published the stock data, shipping times, warehouse logistics, country-by-country delivery commitments, returns policy, price, and credibility signals, in the kind of structured, accurate, consistent detail that makes an algorithm willing to put its name behind a recommendation.
Confidence work laid down years before the moment ChatGPT needed it was compounded into a single won event in 15 minutes flat.
Map your intent cohorts. Score each one against the seven factors. Work out which mode each cohort will use to make which decision. Then train the seven AI employees (Google, ChatGPT, Perplexity, Claude, Copilot, Siri, and Alexa) to represent you with positive sentiment, accurate facts, and consistent narrative across every one of those moments, because they’re already working 24/7, they’re already talking to your customers, and the only question left is whether they’re recommending you or your competitor.
Untrained employees cost you money every day they’re untrained. Trained employees generate revenue every day they’re trained. Won is the moment you’ve trained them for, or the moment they’ve handed to your competition.
The next question is how you measure all of this, and it turns out my answer rewrites how brands should think about measuring AI-era search-assistive-agential success entirely. That’s the next article in the series.
OpenAI is making a clearer push into e-commerce advertising by letting retailers generate ads directly from their product catalogues inside ChatGPT.
What’s happening. Retailers can now connect product feeds to ChatGPT, allowing the platform to automatically create ads using product names, images and attributes, instead of building campaigns manually.
The ads themselves don’t change for users. They still appear beneath responses and are clearly labelled as sponsored.
Why we care. Running ads at scale has been a major barrier for e-commerce brands in ChatGPT.
This update removes that friction, especially for retailers with large inventories, by turning product catalogues into ready-to-run ad campaigns.
Zoom in. Brands set rules for which products to include, then let the system generate ads automatically.
It mirrors how shopping campaigns work on platforms like Google, where structured feeds power both organic and paid visibility.
What’s new. Previously, product data could inform ChatGPT’s answers, but it couldn’t be used for advertising.
Now, that same data powers both, effectively linking organic presence with paid campaigns.
Between the lines. This signals a shift in how OpenAI plans to monetise shopping.
Rather than taking a cut of transactions, it’s moving toward capturing ad budgets already spent on platforms like Amazon and Meta.
What they’re saying. Industry analyst Debra Aho Williamson called feed-based automation “table stakes,” noting that ChatGPT’s edge lies in serving ads based on conversational intent rather than traditional signals.
Ad tech partners like StackAdapt say the setup integrates easily with existing feeds, lowering adoption barriers.
Cost-per-action models are also reportedly in development, pointing to a deeper push into performance advertising.
What to watch. Expect more retailers to test ChatGPT as a performance channel as setup becomes easier. The bigger question is whether conversational intent can drive conversions as effectively as traditional search or marketplace signals.
When a website migration goes wrong, the consequences can be a devastating loss of organic traffic and revenue. But what happens when the damage isn’t immediately visible? What if Google is silently deprioritizing your content, page by page, until your traffic has evaporated?
This is the case study of how a multinational media organization lost 90% of its traffic following a domain migration, and how addressing a seemingly harmless technical issue — soft 404 errors — helped unlock suppressed traffic potential across 13 country-specific domains.
While this case study examines events from 2021–2023, the lessons learned remain timeless and directly applicable to any site facing indexing challenges today.
The catastrophic drop
In January, 2022, the Brazilian localization of a cryptocurrency news website completed a domain migration. After the transition, traffic didn’t just drop — it plummeted. Comparing December 2021 to December 2022, both sessions and pageviews had fallen approximately 90% year-over-year.
According to Google Search Console data, the old domain (xx.com.br) was receiving between 15,000 to 25,000 clicks per day before migration. After migrating to the new subdomain structure (br.xx.com) in January, traffic collapsed and never recovered. It stabilized at around 2,000 to 4,000 clicks per day — a sustained loss that persisted for over a year.
The migration coincided with three major Google algorithm updates in June 2021: the core update, spam update, and page experience update. While these updates caused the expected temporary volatility, the Brazilian site showed no signs of recovery.
Domain migrations typically show an initial traffic drop as Google recrawls and reassesses the site. That’s expected.
Normally, this traffic recovers within weeks or months. In this case, there were no signs of recovery.
The root cause? The old domain continued to be crawled by Google long after the migration.
According to the team’s analysis, proper redirect implementation and technical migration protocols weren’t fully implemented, causing Google to split its crawl budget between two domains rather than consolidating authority on the new one.
In mid-August 2022, after addressing the migration issues with the SEO and IT teams, there was a subtle uptick — a peak of 12 clicks and 37 impressions on Aug. 29, 2022. While modest, this represented the first signs of recovery and indicated that Google was beginning to properly recognize the new domain.
Using Facebook Prophet forecasting on pre-migration data, the team estimated that without the migration issues, the Brazilian site would have exceeded 2 million monthly clicks by early 2022. Instead, it was generating a fraction of that traffic.
Understanding the indexing bottleneck
While fixing the migration was critical, it revealed a deeper problem affecting not just Brazil, but all 13 of the site’s country domains: a massive indexing backlog.
Google’s page processing follows four stages:
Crawl: Google discovers and reads pages.
Render: The page code is rendered.
Index: Pages wait in a queue to be stored in Google’s index.
Rank: Pages appear in search results with rankings.
The Brazilian site was taking an average of 2 minutes for Google to crawl new articles (an acceptable amount of time for a news site). However, indexing these articles was taking 24 hours. For time-sensitive cryptocurrency news, this delay was catastrophic. By the time the site’s articles were indexed, the news cycle had already moved on.
The scale of the site migration problem: 513,000 crawled, but not indexed, pages
In January 2023, Google Search Console revealed alarming indexing issues across all domains:
Crawled – currently not indexed: 513,369 pages (Brazil alone)
Soft 404: 1,193 pages and growing rapidly
Alternate page with proper canonical tag: 2,532 pages
Discovered – currently not indexed: 524 pages
The “Crawled – currently not indexed” issue was particularly concerning. These were pages that Google had successfully crawled but chose not to index. This typically happens when Google considers a page low-quality, duplicate, or not worth the crawl budget.
Upon investigation, the team discovered that converter pages (e.g., “/usd-to-thor?amount=250” or “/eur-to-signaturechain?amount=1000”) were being automatically generated at scale. These thin content pages were consuming Google’s crawl budget, causing it to deprioritize the entire domain.
The soft 404 time bomb
While fixing the migration and removing low-quality pages was important, the most insidious issue was the proliferation of soft 404 errors.
A soft 404 occurs when a page returns a 200 (success) status code but actually contains no meaningful content — essentially a “page not found” that doesn’t properly signal its emptiness to search engines. Unlike hard 404s, which clearly communicate that the page doesn’t exist, soft 404s confuse search engines and waste crawl budgets.
The data revealed this wasn’t isolated to Brazil. Soft 404 errors were growing exponentially across multiple domains:
xx.com (main site): 90,400 affected pages
es.xx.com (Spain): 17,700 pages
kr.xx.com (Korea): 15,400 pages
fr.xx.com (France): 15,100 pages
de.xx.com (Germany): 8,010 pages
Specifically for France, Google Search Console data showed a direct correlation: As soft 404 errors began accumulating in October 2022, total crawl requests dropped from 60,000–70,000 per day to just 20,000–30,000 per day. Google was literally giving up on crawling the site efficiently.
The crawl budget crisis
The concept of crawl budget is critical to understanding why soft 404s matter so much.
Search engines allocate a finite amount of resources to crawl each website. If Google wastes time crawling broken, empty, or duplicate pages, it has less capacity to discover and index your valuable content.
For news sites publishing dozens of articles daily, this creates a vicious cycle: New content doesn’t get indexed quickly, engagement drops, Google further reduces crawl budget, and the problem compounds.
In January 2023, Google was wasting significant resources crawling pages that provided no value. This meant:
Slower indexing of new, timely content.
Reduced visibility in search results.
Lost traffic opportunities.
Degraded domain authority in Google’s eyes.
The systematic fix: Addressing root causes of site migration problems
Starting Jan. 31, 2023, the team implemented a comprehensive technical SEO remediation plan focused on three priorities:
Urgent: Soft 404 resolution
The team identified the source of soft 404 errors and implemented proper HTTP status codes. Pages that truly didn’t exist began returning proper 404 or 410 status codes. Pages with content were fixed to render properly.
High priority: Crawl budget optimization
Removed or noindexed automatically generated currency converter pages.
Implemented stricter URL parameter handling.
Used robots.txt to block low-value URL patterns.
Set up proper canonicalization for variant pages.
Medium priority: Core Web Vitals
While user experience metrics were important, the team recognized that fixing indexing issues would have a more immediate impact than optimizing page speed. Core Web Vitals improvements were addressed, but not at the expense of resolving indexing bottlenecks.
Weeks after implementing the fixes, the impact was measurable:
Brazil (br.xx.com)
Crawled – currently not indexed: Dropped from 513,000 to 220,000 pages (57% reduction).
Soft 404 errors: Reduced from 1,193 to 370 pages (69% reduction).
Traffic recovery: Visible upward trajectory starting early 2023.
Germany (de.xx.com)
Indexed pages: Increased from ~150,000 to 370,748.
Total clicks: Rose from ~8,000/day average to sustained 12,000-15,000/day.
Google Discover traffic share: Jumped from 42% to 58%.
Poland (pl.xx.com)
Indexed pages: Grew from ~100,000 to 135,556.
Total clicks: Increased significantly with multiple traffic spikes above 30,000/day.
Google Discover traffic share: Rose from 15% to 86%.
Spain (es.xx.com)
Google Discover clicks: Increased from ~450,000 to 912,721 total.
Traffic distribution: Discover now represents 65% of total traffic.
All domains combined
By late April 2023, soft 404 errors across all domains had dropped from a peak of approximately 120,000 pages to under 20,000 — an 83% reduction.
Most remarkably, the biggest traffic gains came from Google Discover — Google’s personalized content recommendation feed. As indexing health improved, Google began trusting the domains enough to recommend their content more aggressively to users.
The Core Web Vitals paradox
Interestingly, improvements to Core Web Vitals (page speed, interactivity, and visual stability) showed mixed results:
Desktop improvements:
Germany: 25.1% → 97.1% good URLs
Poland: 20.5% → 68.9% good URLs
Korea: 15% → 84.6% good URLs
Mobile challenges:
Brazil: 0% → 0% (no improvement)
Argentina: 0% → 0%
Thailand: 0% → 0%
Korea: 93.4% → 0.5% (severe regression)
Turkey: 94% → 0% (severe regression)
The team’s hypothesis: Core Web Vitals performance is heavily influenced by regional factors like CDN proximity, server location, network quality, and device capabilities. Countries with poor mobile infrastructure or greater server distance showed minimal improvement despite technical optimizations.
This reinforced an important lesson: Not all technical SEO issues affect all markets equally. A one-size-fits-all approach would have wasted resources by optimizing for metrics that couldn’t improve without infrastructure investment, while the real wins came from addressing indexing fundamentals.
Key technical SEO lessons
1. Indexing issues trump almost everything else
No amount of content quality, backlinks, or page speed optimization matters if Google isn’t indexing your pages. Before optimizing what’s visible, ensure your content is actually being indexed.
2. Soft 404s are silent killers
Unlike hard 404s that immediately alert you to problems, soft 404s quietly accumulate, degrading your crawl budget until you notice traffic declining. Regular monitoring of Google Search Console‘s “Pages” report is essential.
The Brazilian site’s migration issues persisted for over a year. A proper migration protocol should include:
Complete redirect mapping verification.
Confirmation of old domain deindexing.
Search Console property setup and validation.
Multi-week monitoring of both old and new domains.
Crawl rate and indexing speed tracking.
4. Crawl budget is real for high-volume sites
For sites publishing 10+ articles daily across multiple domains, crawl budget optimization is not optional. Automatically generated pages, URL parameters, and infinite scroll implementations can quickly consume available crawl resources.
5. Regional differences demand regional solutions
Core Web Vitals data showed that Brazil, Argentina, and Thailand couldn’t achieve the same performance as European markets. Instead of forcing uniform standards, prioritize fixes tailored to each market that can actually succeed.
6. Google Discover is increasingly critical
For news and timely content publishers, Google Discover accounts for a substantial share of traffic in some markets. But Discover only promotes content from sites Google trusts — and technical issues like soft 404s directly erode that trust.
Practical site migration implementation guide
For teams facing similar challenges, here’s a systematic approach:
Weeks 1-2: Audit and prioritize
Access Google Search Console for all properties.
Export “Page indexing” reports for all domains.
Identify the scale of each issue category.
Calculate the trend (growing, stable, or declining).
Prioritize based on issue volume and growth rate.
Weeks 3-4: Fix soft 404s
Sample 20–30 URLs from the soft 404 report.
Identify common patterns (empty pages, broken functionality, etc.).
Implement proper HTTP status codes (404, 410, or fix the content).
Validate fixes in Google Search Console.
Monitor for reduction in affected pages.
Weeks 5-8: Address crawled but not indexed
Analyze URLs to identify auto-generated content.
Implement robots.txt rules or noindex tags for low-value pages.
Review and strengthen internal linking to important pages.
Ensure proper canonicalization across variants.
Request reindexing via Search Console for key pages.
Weeks 9-12: Monitor and optimize
Track indexing coverage weekly.
Monitor crawl rate changes in Search Console.
Measure organic traffic recovery.
Identify remaining outlier issues.
Document learnings for future migrations.
Calculating the traffic loss from migration issues
How significant was this suppressed traffic opportunity?
According to Facebook Prophet forecasting based on pre-migration data, the Brazilian site was trending toward 20,000+ daily clicks. At the time of fix implementation in early 2023, it was receiving approximately 5,000–7,000 daily clicks. This represented roughly 6575% of potential traffic being suppressed — or conversely, the site was only achieving 25–35% of its forecasted potential.
More broadly, across all 13 domains, the soft 404 and indexing issues prevented approximately 500,000 pages from being indexed. Given average click-through rates for indexed pages, this represented millions of potential monthly impressions and hundreds of thousands of potential clicks being left on the table.
The most important lesson from this case study is that technical SEO issues don’t stay static — they compound. What starts as a few hundred soft 404s becomes thousands, then tens of thousands.
Google’s response isn’t immediate punishment, but gradual deprioritization. Traffic doesn’t crash overnight; it bleeds slowly.
For the Brazilian site, it took over a year to recognize the full scope of the problem. During that year, competitors filled the gap, topical authority eroded, and recovery became exponentially harder.
The good news? Once identified and systematically addressed, these issues are fixable. Within 12 weeks of implementing the remediation plan, every domain showed measurable improvement. Some saw traffic double or triple.
Technical SEO is often seen as unglamorous maintenance work. But as this case demonstrates, it’s the foundation upon which all other optimization rests. Before worrying about AI-generated content, E-E-A-T signals, or the latest algorithm update, ensure Google can actually find, crawl, and index your content.
Because the best content in the world is worthless if it’s trapped outside search engine indexes.
Cybersecurity researchers have flagged a new version of the TrickMo Android banking trojan that uses The Open Network (TON) for command-and-control (C2).
The new variant, observed by ThreatFabric between January and February 2026, has been observed actively targeting banking and cryptocurrency wallet users in France, Italy, and Austria.
"TrickMo relies on a runtime-loaded APK (dex.module),
Googlebook, Google’s planned replacement for ChromeOS, has been unveiled Later today, Google is due to unveil “Googlebook”, the company’s new category of Android-powered laptops. These devices appear to be Google’s successor to ChromeOS. This new OS will feature Google’s Chrome browser, the Google Play Store, and Gemini AI integration. Based on the slide below, Googlebook […]
“All Modern Operating Systems do this” – Except Windows… – Microsoft defends Windows 11’s planned “Low Latency Profile” Last week, we reported on Windows 11’s Low Latency Profile (LLP), a new feature that should dramatically speed up certain OS tasks. Microsoft’s new “Low Latency Profile” (LLP) for Windows 11 will crank up CPU frequencies for […]
While we wait for Memorial Day, Amazon already has its best-sellers on sale, with up to 50% off top brands like Bissell, Apple, Dyson, Ninja, and more.
As Dutton Ranch debuts on Paramount+ on May 15, Marshals enters its final few weeks. According to one Yellowstone star, a Beth and Kayce Dutton crossover isn't out of the question.
The maker of the Canvas school software said it "reached an agreement" with the hackers, but provided no guarantees that the hackers would not release the data or keep their word.
TikTok is systematically converting its discovery engine into a transaction layer, which both deepens user retention and opens entirely new revenue streams for its new owners.
WinUI is a key part of Microsoft's initiative to fix Windows 11, and that framework is being updated. Here's how those improvements will show up on your PC.
The WD_Black SN850X is currently enjoying a major price drop on Amazon for its gigantic 4TB model, with several bonus discounts for its 1TB, 2TB, and 8TB models for a limited time.
NVIDIA has released the GeForce 596.49 WHQL Game Ready driver with day-one support for Forza Horizon 6, Directive 8020, and Subnautica 2. The driver also enhances smoothness when DLSS Frame Generation is used with V-Sync, fixing a notable gaming bug.
On the general bug fix side, this release resolves a viewport flickering issue in Foundry Mari 7.0v2. Grab the driver from the link below.
Micron Technology, Inc. (Nasdaq: MU), today announced it has sampled 256 GB DDR5 registered dual in-line memory modules (RDIMM) to key server ecosystem enablers. The module is built on the company's leading-edge 1-gamma technology, which is capable of speeds up to 9,200 megatransfers per second (MT/s), greater than 40% faster than modules in volume production today. Micron's module employs advanced packaging techniques, 3D stacking (3DS) multiple memory dies connected by through-silicon vias (TSVs). Combined with Micron's 1-gamma DRAM, these innovations provide the capacity, speed and power efficiency required to scale next-generation AI systems. A single 256 GB module can reduce operating power by more than 40% versus two 128 GB modules, enabling greater efficiency for modern AI data centers.
Ecosystem partner validation
Micron is collaborating with key ecosystem enablers to validate the 256 GB 1-gamma DDR5 RDIMM across their respective current and next-generation server platforms. This co-validation ensures broad platform compatibility and accelerates the path to production deployment for data center customers building AI and HPC infrastructure at scale.
Desktop monitor shipments reached 133.4 million units in 2025, growing 4.3% year-on-year, signaling a recovery from post-pandemic disruptions. This expansion reflects the evolution of monitors into versatile, high-value tools for laptop-dominated environments, with gaming fueling interest in high-performance displays.
Gaming monitor shipments are projected to expand to 43 million units in 2026, supported by increased cost-effectiveness and added functionality. This trend reflects a shift toward specialized consumer applications and immersive entertainment experiences.
SiFive, Inc., the gold standard for RISC-V computing, today announced the launch of the SiFive Performance P570 Gen 3, the most powerful and efficient out-of-order processor core in its class. Purpose-built for demanding edge AI, high-end consumer, and commercial IoT applications, the P570 Gen 3 delivers a large leap in performance compared to the popular P550 Gen 1, and also provides the most modern RVA23 ISA profile support.
This versatile IP can be used as the control processor in embedded IoT devices, running a full networking stack, or can be used as the main applications processor in consumer devices, running rich OSs, such as Android or enterprise-grade Linux. The high-performance vector unit supports running AI models and inference on edge devices.
SCUF Gaming, Innovators in the high-performance gaming controller category and part of the Corsair family of brands, today unveiled SCUF Omega, a performance controller designed from the ground up and officially licensed for PlayStation 5 and PlayStation 5 Pro consoles. Built on 15 years of innovation and esports championships, SCUF Omega represents the company's most advanced controller to date, delivering its fastest and most customizable gaming experience yet. The SCUF Omega is now available worldwide, compatible with PlayStation 5 consoles, PC, Mac, iOS, and Android.
With more than 160 patented innovations, SCUF has always focused on giving its players an edge so they can perform at the highest level. Omega is designed to reflect everything the company has learned from competitive play, delivering speed, accuracy, and personalization. "For 15 years, SCUF has pushed the boundaries of performance, driven by pro player insights, relentless innovation, and an unwavering passion for the game." said Tobias Brinkmann, Senior Vice President and General Manager of Gaming Peripherals at Corsair. "Omega is the realization of that journey, and the beginning of what comes next."
Corsair is excited to announce widgets for the XENEON EDGE 14.5" LCD Touchscreen are now on the Elgato Marketplace. This gives XENEON EDGE owners a new and growing platform to browse, download, and install software for their device for expanded customization. Additionally, independent developers and makers can create widgets for the XENEON EDGE, even with no coding experience. Custom-made widgets can be for personal use, and will be able to be submitted to the Elgato Marketplace for the community to purchase or download in the future.
Integration with the Elgato Marketplace will significantly expand both the number and variety of widgets available for XENEON EDGE, adding even more functionality and value to what is already an incredibly flexible and customizable device. As a bonus, the rollout includes over 20 first-party widgets that are free to download and are available immediately.
Origin Code, a performance-driven brand pushing the boundaries of hardware, today announces the latest expansion of its Vortex DDR5 family: a newly optimized 48 GB (24 GB × 2) kit running at 6200 MT/s CL28, in the striking Meteorite Black finish, will be launched at Computex 2026.
Complementing this launch, Origin Code also introduces a purpose-built independent watercooling block, designed to further enhance thermal efficiency and unlock sustained performance for high-end systems
The project was announced in May 2024 during Kenyan President William Ruto's state visit to Washington. G42 was expected to lead construction of the Olkaria facility in Kenya's Rift Valley, with Microsoft using it to launch a new East Africa cloud region for Azure. The first phase was supposed to...
The change leaves the FCC's broader policy intact. Rules adopted in March block approval of new consumer routers manufactured outside the United States, part of an effort the commission says targets national security risks in foreign supply chains. That restriction remains in place, with exemptions granted selectively to companies the...
The retail giant told KCRA 3 News that it will no longer sell e-bikes in California that go faster than state law allows. The decision follows a consumer alert from California Attorney General Rob Bonta, who reminded buyers and sellers that the state divides e-bikes into three classes: Class 1...
iPhone owners who want to text users of non-Apple devices more securely should install iOS 26.5, which Apple released on Monday. The update introduces support for end-to-end encryption when using Rich Communication Services (RCS). The encryption, which makes messages unreadable outside the sending and receiving devices, is available to users...
On September 1, 2026, the price of a Nintendo Switch 2 console will increase across several markets as the world of consoles becoming more expensive the longer they're around instead of less, continues. After that aforementioned date, the minimum price to enter the Switch 2 generation is a cool $499.99 USD, but before that goes into full effect, you can pay that price for a Switch 2 over the summer and get one of three major first-party games to go along with it. Nintendo has announced a new 'Choose Your Game Bundle' for the Nintendo Switch 2, which gets you […]
Applied Materials partners with TSMC in a $5 billion EPIC Center to advance semiconductor technologies for AI-driven innovation and efficiency. Applied Materials and TSMC Partner at the EPIC Center to Accelerate AI Scaling Press Release: Building on more than 30 years of collaboration, Applied Materials, Inc., today announced an innovation partnership with TSMC to accelerate the development and commercialization of semiconductor technologies required for the next era of AI. Working together at Applied’s EPIC Center in Silicon Valley, the companies will co-innovate to advance materials engineering, equipment innovation, and process integration technologies designed to deliver energy-efficient performance from the data center to the […]
Sipeed has unveiled its new RISC-V powered SBC platform, the K3 series, which can run up to Qwen3.5 35B AI LLMs and start at $299. The Sipeed K3 SBCs Pack A Punch For AI LLMs In a Compact "Pico-ITX" Form Factor, Up To 32 GB Memory Support Chinese manufacturer, Sipeed, has partnered with SPACEMIT to launch its brand new K3 series SBCs or Single-Board Computers (such as the Raspberry Pi). These PCs are normally aimed at AI, Edge, and Networking applications. Sipeed has leveraged SPACEMIT's Key Stone K3 AI CPUs, which are based on the RISC-V architecture, and offer some […]
Jensen Huang was reportedly not invited to President Trump's state visit to China, even though the Nvidia CEO has accompanied the U.S. president in several state visits across the globe. One expert says that this is a "strong signal" to Beijing that Washington won't budge on its stance of banning the export of high-end chips to China.
Nowtown connects people with local events, spaces, and services. Users can browse offers nearby, book online, and check in digitally—all in one place with secure payments.
Providers create listings for spaces, events, or services, manage bookings, and reach new audiences through the community. Nowtown is live in Germany and in its early growth phase.
Wikipedia was once widely considered an unreliable source. Today, however, it’s often treated as a credible reference point because of its extensive citations and collaborative editing process.
It’s also one of the primary sources AI search systems rely on. Alongside Reddit, Wikipedia heavily influences the information surfaced by ChatGPT and Google.
The downside to this is that Wikipedia isn’t always foolproof. Negative or outdated information often persists on certain pages for months or even years. That information is then funneled back into AI search systems and relayed to users.
This creates a feedback loop where outdated or negative narratives can gain long-term visibility and credibility across AI search platforms.
So, how does one navigate the scenario when negative information ends up on Wikipedia?
How content ends up on Wikipedia
One of the main criteria of getting information on Wikipedia is verifiability. Media outlets and Wikipedia users verified by the platform itself are often the main providers of content.
For instance, respected third-party outlets such as news organizations and scientific journals are often the main sources. This leads to these outlets serving as gatekeepers of sorts.
It also means that verifiability is sometimes prioritized on Wikipedia over pure accuracy of content. Unfortunately, media outlets don’t always achieve 100% accuracy in their reporting.
Another issue is that Wikipedia’s editors are often decentralized volunteers. This means that content uploaded to the platform is often based on general consensus.
The result is that there’s no central authority on Wikipedia that can quickly “fix” disputed content.
Wikipedia openly acknowledges that controversies surround the platform. It even maintains a page documenting those disputes over the years.
Negative or outdated information can persist for several reasons. In many cases, it also originates from a single high-profile news story or legal issue that continues to be cited long after the situation changes.
Citations
Wikipedia citations have extreme permanence. Once information is essentially backed by a “reputable” and verified source, removal from the platform becomes extremely difficult. Even information that has long since been disproven can remain on Wikipedia if it comes from a proper source.
The echo chamber effect
The web is a highly influential sphere. Wikipedia serves as both the influencer and the influenced in terms of absorbing and spewing information. Negative claims often circulate and reinforce themselves through Wikipedia — and this is only becoming more prominent with AI search platforms.
Risk aversion
Simply put, Wikipedia’s editors don’t want to be viewed as biased. This means they often avoid removing content from verified sources.
Differing news coverage
Negative stories often receive more coverage than positive ones. Corrections also tend to attract far less attention than the original reports, creating an imbalance in the sources Wikipedia relies on.
Wikipedia’s role in AI search
Wikipedia has become a major source for generative AI platforms, giving its content an added layer of credibility in AI-generated answers.
ChatGPT and Google AI Overviews frequently condense information from Wikipedia and other sources, such as Reddit and news outlets, into simplified narratives. As a result, outdated controversies or disputed claims can quickly spread to large audiences.
The issue is compounded by changing user behavior. Many users now rely on AI-generated summaries instead of clicking through to verify information themselves. Some estimates suggest roughly 40% don’t fact-check AI search results.
That means when AI systems surface negative Wikipedia content, it can shape perception almost instantly.
How Wikipedia and AI disrupted a social media company
My online reputation management company recently helped repair the image of a prominent marketing company. (For the sake of privacy, we’ll refer to them as Organization Z.)
Organization Z faced plagiarism claims nearly a decade ago. These claims were eventually cleared and dismissed, with any hint of wrongdoing squashed. However, the claims appeared on Organization Z’s Wikipedia page, where they were labeled a “controversy.”
Making matters worse was that far more attention was paid on Wikipedia to the apparent “controversy” than to the fact that Organization Z’s name was eventually cleared.
AI search engines then began to pull this information directly from Wikipedia. When users searched for the brand online, they encountered terms such as “controversy” and “plagiarism” despite all claims having been dismissed.
The controversy continued resurfacing online years after the claims had been dismissed.
How to navigate negative content on Wikipedia
Before diving into solutions, it’s important to understand what doesn’t work. Editing your own Wikipedia page creates a conflict of interest, and Wikipedia edits are closely monitored. You also can’t remove content without a strong policy-based justification, as the platform has strict standards around sourcing and removals.
With that in mind, here is a practical, step-by-step framework many ORM specialists recommend for addressing negative or outdated Wikipedia content.
1. Perform an audit
Identify the claims circulating on Wikipedia, along with the sources used. Outline any outdated references or integrity gaps.
Determine whether the information on the page is still relevant and whether the coverage is fair and balanced.
2. Compare Wikipedia to current coverage
Compare the Wikipedia page with how the brand, person, or issue is currently represented online. In this context, it’s the same step you would take while performing an AI narrative audit.
Identify whether important context is missing, outdated, or overemphasized. The goal is to spot gaps between reality and the narrative Wikipedia presents.
3. Address the citations
Now that you’ve identified mismatches and analyzed the sources Wikipedia is using, you can begin to address those citations. You’re not altering Wikipedia itself. You’re altering what Wikipedia cites.
Aim to publish factual, positive content that reflects the current reality. Prioritize third-party mentions on reputable media outlets or in academic journals.
4. Strengthen positive, balanced coverage
Build your brand image online with a specific focus on highlighting achievements and industry recognition. Make it clear that you’re a reputable voice in your industry, and Wikipedia will soon reflect that.
Wikipedia remains a powerful source of information, but its reliance on citations and consensus can allow outdated or negative narratives to persist.
That becomes more consequential when AI search engines amplify those narratives in generated answers.
While brands can’t directly control what appears on Wikipedia, they can influence the sources that shape it. The key is to strengthen accurate, balanced coverage across reputable outlets and regularly audit how your brand appears online.
Why do the Riskiest SOC Alerts Go Unanswered?
Security operations teams are drowning in alerts. But the real problem isn't always alert volume; it's the blind spots. The most dangerous alerts are the ones no one is investigating.
A recent report from The Hacker News examined why certain high-risk alert categories - WAF, DLP, OT/IoT, dark web intelligence, and supply chain signals- consistently
The RingConn Gen3 is now available to pre-order, and it's looking like a good subscription-free alternative to Oura — even plugging some gaps in its feature set.
After finally getting my hands on the PS Portal, I decided to re-play my favorite game of all time — here's what I liked about using Sony's handheld device, and what could be improved.
Forza Horizon 6 may have been leaked by a reviewer or insider with early access Playground Games has confirmed that a build of Forza Horizon 6 leaked ahead of launch. The company has stated that the leak did not result from a “preload issue” for Forza Horizon 6. This contradicts all early reporting about the […]
As generative AI moves from cloud-based training to specialized local fine-tuning, the demand for stable, high-wattage on-premise power has never been greater. FSP Group, a global leader in power supply technology, today officially unveiled the FSP2000-57APB, a 2000 W ATX 3.1 flagship power supply specifically engineered for high-performance local AI computing and dual-GPU workstations.
Uncompromising Stability for On-Premise AI Fine-Tuning
Under the annual theme "Powering AI Together," FSP addresses the critical need for data privacy and low-latency processing in AI development. The FSP2000-57APB is purpose-built for secure, in-house compute workloads, such as large-scale model fine-tuning. It effortlessly manages massive power excursions, ensuring that hardware remains protected and systems remain stable during the most intensive deep learning cycles.
DAREU today announced the global release of its GT87 magnetic switch keyboard, introducing a new approach to combining magnetic sensing performance with a mechanical-like typing experience. The GT87, which debuted in China in March, has gained early market traction and was recently recognized with the Red Dot Design Award for product design and user experience.
At the core of the GT87 is a custom magnetic switch integrating TMR (Tunnel Magnetoresistance) technology. Compared with conventional Hall-effect solutions, TMR enables lower power consumption while maintaining precise input detection, supporting tri-mode connectivity across wired, 2.4 GHz wireless, and Bluetooth.
MSI, a global leader in AI computing and high-performance technology, has been honored with multiple Red Dot Design Award 2026 wins, showcasing a diverse portfolio that combines performance, innovation, and refined design across various categories. Among the award-winning products are the PRO MAX All-in-One PC Series, designed for modern workspaces with ergonomic versatility and a clean aesthetic; the MEG X870E ACE MAX motherboard, featuring premium craftsmanship and next-generation performance; the MEG CORELIQUID E15 360, which redefines liquid cooling with advanced engineering and a striking AMOLED display; the MEG MAESTRO 900R, a flagship PC case that merges architectural design with flexible system configuration; and the MSI Stealth 16 AI+, a slim, high-performance laptop with Copilot+ technology that offers portability along with advanced AI capabilities for gaming, creation, and productivity. Together, these innovations highlight MSI's commitment to merging cutting-edge technology with refined, user-centric design.
PRO MAX All-in-One PC Series - Thoughtful Design for Modern Workspaces
The PRO MAX All-in-One PC Series is designed to enhance the modern workplace with advanced performance, ergonomic design, and a sleek aesthetic. Available in 24" and 27" sizes, this series features a clean, minimalist industrial design in black or white, enabling seamless integration into both office and home environments.
With the CHERRY XTRFY K33 Compact Wireless, CHERRY XTRFY presents a flexible gaming keyboard that combines the key features of modern gaming peripherals in a compact and accessible package. Designed for an easy start, the K33 Compact Wireless is aimed at those looking for an affordable entry point without compromising strong connectivity, reliable performance and a comfortable mechanical-like typing experience.
Maximum flexibility and reliable performance
The CHERRY XTRFY K33 Compact Wireless offers maximum flexibility thanks to its tri-mode connectivity: It can be connected via 2.4 GHz wireless, Bluetooth or USB. This not only allows it to be used with a variety of devices but also enables you to switch quickly between your gaming setup, laptop or mobile devices without having to change connections or interrupt your session.
Security researchers at Intrinsec released "BitUnlocker," a tool bypassing Windows 11 BitLocker encryption in under five minutes. This exploit leverages a downgrade attack to pry open drives, exploiting the gap between software patching and certificate revocation. Rooted in CVE-2025-48804, a vulnerability patched in July 2025, the flaw resides within the Windows Recovery Environment and System Deployment Image mechanism. Here's the good news: an attacker needs physical access to the target machine.
Attackers with physical access can use a flash drive to feed the boot manager a legitimate Windows Imaging Format file for integrity checks while appending a malicious payload. The system verifies the clean file but blindly boots the attacker's code, granting access to the decrypted volume. The true danger lies in the downgrade vector. Because Microsoft's legacy Windows PCA 2011 certificate remains globally trusted by Secure Boot, attackers simply load an older, vulnerable boot manager, which the system authenticates without hesitation.
The material, known as SS-H2, is designed to remain stable where conventional stainless steel fails. The work, published in Materials Today, builds on Huang's long-running Super Steel research program, which has previously produced ultra-strong alloys and antimicrobial stainless steel.
According to VideoCardz's report, the Radeon RX 9050 will be a lower-clocked Navi 44 model positioned below the Radeon RX 9060 series in AMD's product stack.
After the initial surge, the GPU prices are dropping gradually, at least in Germany. They are now at just 9% higher than in September 2025. German GPU Listings Show GPU Prices Surged to 120% In February Before Dropping To 112% in May, Bringing Relief to the Hardware Market The GPU market has begun to stabilize, and while it's not the same in every region, a few places are seeing gradual price drops over the last few weeks. A phenomenon that was hard to imagine is finally occurring in some regions. The latest stats show that the GPU selling prices have […]
A new color variant of one of the best PC fans ever made is now available for purchase, as Noctua announces its official launch. Noctua Rolls Out NF-A12x25 G2 Chromax.Black Fan at $34, the Black Edition of the Iconic NF-A12x25 G2 The original Noctua NF-A12x25 was a huge success as it was deemed as one of the best, if not the best, PC fans ever made. Based on the same design, Noctua launched the NF-A12x25 G2 last year, but it was only available in the classic brown-beige color combination. However, Noctua has now officially launched its black version, called the […]
The quarterly financial week for developers and publishers continues with NEOWIZ posting revenue of KRW 101.4 billion (around $74 million) in Q1 2026, up 13.9% year-on-year but down 4.6% quarter on quarter, with no new releases during the quarter. Operating profit came in at KRW 7.0 billion ($5.1 million), down 32% YoY, while net profit surged to KRW 15.5 billion ($11.3 million), a massive 153% year-on-year gain thanks to FX gains from the strong dollar. Mobile led growth via Browndust 2 anniversary events, while PC/Console revenue stabilized on the back of the Lies of P DLC Overture and the indie game Shape of Dreams. NEOWIZ also revealed its full development pipeline of six […]
Microsoft says attackers compromised the mistralai PyPI package with malware that executed on import, while researchers link related npm compromises affecting TanStack and Mistral SDKs to the broader “Mini Shai-Hulud” supply-chain campaign.
SupportAssist Remediation is a background service that Dell bundles on its Windows PCs to automate system recovery and repair tasks, and a recent update is reportedly causing BSOD loops.
AI-assisted bug detection has massively accelerated the timeline in which new security vulnerabilities are discovered, and one researcher argues that has killed the standard 90-day disclosure policy.
Klyft combines data from Apple Watch, Garmin, Oura, Fitbit, and many more wearables into a single 0–100 daily health score. This score blends sleep quality, training load, nutrition balance, and recovery readiness, based on over 800 peer-reviewed studies in sleep science, exercise physiology, and nutrition. Users connect their wearables, log meals by text or photo, and receive workouts and daily recommendations that adapt to their current recovery and goals. The scoring engine is deterministic; AI is used only for coaching language, meal analysis, and conversational guidance, not for scoring itself. Available on iOS.
Agentic AI is already running in production environments across many organizations today. It is executing tasks, consuming data, and taking actions — most likely without meaningful involvement from the security team. The industry conversation has largely framed this as a question of policy: allow it, restrict it, or monitor it? However, that framing misses the point.
The more urgent
RAM prices remain out of control, and bad actors are taking advantage of honest buyers with a wide range of scams. Here's how they work and how you can protect yourself next time you buy memory.
WWE has announced that Gears of War: E-Day, the highly anticipated prequel to the Gears of War series, will be a sponsor for an upcoming PLE event called Triplemania 34. Given past video game sponsorships, people are speculating that this event could provide hints when Gears of War: E-Day will release.
Microsoft's Israeli subsidiary has been placed under ownership of Microsoft France in the interim, after a Microsoft investigation reportedly uncovered "unethical" use of its products violating its terms of service and code of conduct.
Microsoft CEO Satya Nadella testified in the ongoing Musk v. Altman trial, indicating that the billionaire didn't raise any issues about the partnership and investments despite having his phone number.
Here We Go Again, or: Why GPU Bottlenecks Hide True CPU Performance. Gamers keep demanding 1440p CPU benchmarks, but higher resolutions often hide the very performance differences CPU testing is supposed to reveal. Here's why 1080p still matters most.
During last week's earnings call for its Q4 FY25 and full-year 2025 financial report, Sony's executives admitted they haven't decided on the launch timing for the PlayStation 6 due to ongoing memory shortages, and thus very high prices that could drive the system's launch price past what many consider reasonable for a gaming console. According to known AMD leaker KeplerL2, the only reasonable cutbacks Sony could make without gutting the system heavily to keep its price as low as possible would be to reduce the memory bus and the system's RAM. "Nerfing the specs so much kinda defeats the point of having a […]
A near-complete gaming PC bundle from Newegg saves you $769. The combo includes a 9850X3D, RTX 5070 Ti, 2TB SSD, 32GB of DDR5 RAM, 240mm AIO cooler, and an X870E motherboard for $2074.
The public-private partnership aims to develop an SoC that offers 100x the computing power of current chips designed for spaceflight. NASA envisions that the technologies developed from this project will also be widely implemented on Earth-bound applications, like the automotive and aerospace industries.
StrideFlow is an AI goal planner that builds a weekly schedule around your real life. It audits your availability, work rhythm, sleep and recovery, and recurring commitments, then turns goals into time blocks you can actually follow. Fixed commitments stay put while flexible blocks shift as your week changes, so plans survive surprises and you keep momentum.
RCQ is an end-to-end encrypted messenger that replaces phone numbers and emails with a network-issued UIN. Messages use sealed-sender X25519 and ChaCha20-Poly1305 with Ed25519 signatures, so servers see only ciphertext and the recipient address. You can make peer-to-peer audio and video calls via DTLS-SRTP, join persistent audio rooms, or try five-minute Random Chat. History stays on your device, with no ads, trackers, or analytics, and you can burn your account at any time.
SEO used to be constrained by one thing more than anything else: dependency.
Dependency on developers, roadmaps, and “maybe next quarter.”
If you wanted a new page template, a calculator, a comparison widget, or even a simple interactive component, you had to ask, wait, and compromise. That’s changing fast.
If you’re in SEO or GEO today and you’re not learning how to vibe code, you’re limiting your impact.
Vibe coding changed the power dynamics in SEO
A few years ago, building tools like calculators or interactive widgets meant tickets, specs, and dev cycles.
Today, with AI, I’ve personally built dozens of mini apps, tools, and UI components without involving a single developer.
Some of those tools are small. Some are relatively ugly but effective. Some now bring in thousands of organic sessions per month.
Entire pages built around a vibe-coded tool are now outperforming traditional text-heavy competitors.
Parents Hub “Back To School Countdown” Vibe-Coded Tool
Even more importantly, I’ve introduced this mindset to my SEO team, and they’re now building tools on their own to achieve our search goals. That alone changes everything.
SEO teams can now move faster, test ideas immediately, and reserve developers for actual engineering work, including new templates, infrastructure, and scaling.
And yes, there’s something genuinely satisfying about building a tool yourself, publishing it, and watching it attract traffic month after month.
You don’t need to build fancy things. Just things that get the job done.
Stop talking about user personas. Start talking to them.
Everyone agrees on the user persona theory:
Identify user personas.
Understand their pain points.
Create content that addresses them.
What almost no one explains is how to actually present that information.
Historically, SEO handled personas with text:
“If you’re a parent…”
“For families…”
“Business travelers should consider…”
That approach is already outdated. Today, we can let users self-identify and surface only the information that matters to them.
One example from a brand I manage:
A vibe-coded tabbed component.
Each tab represents a different user persona.
Clicking a tab reveals persona-specific content.
For airport transfers in Majorca, a “family” persona doesn’t care about the same things as a solo traveler.
Example case of the “User Persona” component
They care about vehicle safety, child seats, family-friendly routes, vehicle size, and indicative pricing. That content appears only when the Family tab is selected.
From an SEO and GEO standpoint, persona pain points were sourced directly from Google Search Console and query fan-out analysis.
The component was then vibe-coded and placed where intent needed to be satisfied immediately.
This aligns with how AI platforms already structure answers: segmented, persona-aware, and intent-first.
Entire traffic categories can be built on tools alone
On one personal project, we launched a brand-new Tools category — ten pages with simple tools, such as:
Calculators.
Checklists.
Calendars.
Countdown timers.
AI generators.
Each page leads with the tool and uses supporting components to answer sub-intents.
The result? More than 5,000 incremental clicks in two months. Most of those pages were also out of season.
One page we published targeted a Greek government school financial support program with a high-volume head term, dozens of long-tail queries, and extremely text-heavy competition.
We built:
A financial support eligibility tool.
A transparent explanation of the algorithm logic behind the tool for E-E-A-T.
Common rejection mistakes parents made when applying for support.
Historical program changes.
A step-by-step application flow.
Parents Hub Kindergarten Financial Support Eligibility Calculator
We tagged the tool as a WebApplication, implemented HowTo schema for the process, and properly marked up the FAQs.
Three days after publishing, the page was already ranking on the first page for the main term and generating about 100 clicks.
Sometimes SEO really doesn’t take that long if you solve the problem better than anyone else.
Tools are the ultimate SEO and PR assets
Some tools are built purely for traffic. Others are designed to become linkable digital assets.
A pregnancy due date calculator, a baby name generator, or a comparison table based on TripAdvisor data isn’t just a page. It’s a potential PR campaign.
When a digital asset solves a real pain point, looks modern, answers intent better than SERP features, and has clear PR angles, that’s where SEO, PR, and branding start to collide. That’s when things get really interesting.
Finding tool-page opportunities is easier than ever
With MCP servers from SEO tools, you can now surface tool ideas directly from search demand without leaving the chat, assess difficulty instantly, and launch faster than ever.
I’ve built and launched multiple tool pages this way, and the speed difference compared with traditional workflows is massive.
We’re entering a period where ideation, validation, and execution can all happen in days, not months.
SEO is no longer about who can write the longest article, rephrase the same information better, or game templates. It’s about who answers intent fastest, removes friction, and builds search experiences instead of documents.
Vibe coding changed who gets to build. And right now, the people embracing it are pulling away fast. If you want to win in modern SEO and GEO, build tools, build components, and build search experiences. Text alone isn’t enough anymore. And honestly, that’s a very good thing.
TeamPCP, the threat actor behind the recentsupply chain attack spree, has been linked to the compromise of the npm and PyPI packages from TanStack, UiPath, Mistral AI, OpenSearch, and Guardrails AI as part of a fresh Mini Shai-Hulud campaign.
The affected npm packages have been modified to include an obfuscated JavaScript file ("router_init.js") that's designed to profile the execution
Noctua’s premiere 120mm fans are now available in Chromax Black It’s official, Noctua’s best-performing 120mm fans, the NF-A12x25 G2, are now available in Chromax Black. Now, PC builders who dislike Noctua’s iconic Brown/Beige colour scheme have an all-black option. These new fans are available as a single, standalone fan and as a speed-offset dual-fan pack. […]
Intel to return to on-package memory with Razor Lake-AX – Leaker claims Intel’s long-rumoured Razor Lake-AX processor is shaping up to be a fascinating piece of silicon. This processor reportedly combines next-generation (post-Nova Lake) CPU cores with a powerful ARC integrated graphics solution (iGPU). Now, according to the leaker Haze2K1, Intel has chosen to pair […]
A new report from Rebs Gaming claims Halo Infinite’s multiplayer narrative cutscenes were originally building toward Project Tatanka, Halo’s canceled Battle Royale-inspired project, before layoffs at 343 Industries reportedly led to the storyline being scrapped.
Kingston Digital, Inc., the Flash memory affiliate of Kingston Technology Company, Inc., a world leader in memory products and technology solutions, today announced it has shipped more than 100 million units of the Kingston A400 SATA solid-state drive. Launched in 2017, the Kingston A400 quickly gained recognition for its impressive performance in terms of booting, loading, and transferring data when compared to traditional hard drives.
The Kingston A400 SATA SSD boasts remarkable read/write speeds of up to 500 MB/s and 450 MB/s, respectively. This significant speed enhancement provided customers with a performance improvement over conventional hard drives. With this level of efficiency, the A400 series became a preferred choice for consumers seeking enhanced data transfer rates and overall system responsiveness.
Noctua today presented the much-anticipated black version of its award-winning NF-A12x25 G2 120 mm flagship fan. Available in single-fan and speed-offset dual-fan packs, the new chromax.black variants provide the same state-of-the-art quiet cooling performance for PC cases and water cooling radiators as the regular NF-A12x25 G2, just in a sleek all-black design.
"The first-generation NF-A12x25 was one of the most successful Noctua fans of all time, so the G2 version had big shoes to fill," says Roland Mossig (CEO of Noctua). "We've been extremely pleased with the excellent response from both customers and expert reviewers, so we're excited to follow up with the chromax.black variants today."
Memory makers like Samsung, SK hynix, and Micron are currently striving to find the delicate balance between supplying the world with enough DRAM and expanding their production capacity by placing large new orders for the semiconductor fabs used to produce the memory. According to SK Group chairman Chey Tae-won, who also oversees SK hynix, if companies like SK hynix do not increase their memory supply, customers will find ways to use less memory by optimizing their infrastructure and software for much lower utilization. At present, hyperscalers and AI accelerator makers such as AMD, NVIDIA, and others are securing as much memory as possible. This is part of AI data center expansion, which requires more GPU and CPU DRAM to support large training runs and maintain massive model inference, now reaching tens of trillions of parameters and needing hundreds of gigabytes of system memory to host a single model for just a few users.
This demand has created a supply chain issue where memory makers are selling all of their available DRAM months in advance but are hesitant to significantly expand manufacturing capacity, despite recognizing the increase in demand years ago. Memory makers are the first to notice rising demand, and their reluctance to increase manufacturing capacity is contributing to the current memory shortage. However, they are also wary of expanding production capacity as it takes years to build new memory fabs, just as projected demand is expected to stabilize. SK hynix has ordered about 20 Low-NA EUV machines from ASML for their expansion plans, which will also support future storage production once the tools are operational. However, all of this added capacity is still years away, and we will remain in a tight situation for a little while longer.
Resident Evil Requiem is among the best-looking survival horror games of the current console generation, but if you are on PC and have the performance headroom to spare, you can push the game's visuals to a level past what CAPCOM intended with the Graphics Enhancement mod now available for free on Nexus Mods. "Resident Evil Requiem ships with a maximum in-game RT setting of High. This mod breaks that ceiling — pushing raster quality further, improving RT visuals across the board, and squeezing out a little extra quality from path tracing as well. Everything is tuned from a clean in-game […]
Power supplies for a special protective cable will start shipping soon as Cooler Master begins taking pre-orders. Cooler Master GPU Shield-Compatible MWE Gold V4 Goes On Pre-Order in China; Just Buy Demonstrates GPU Shield Features Not just ASRock and ASUS, Cooler Master has also prepared a special 16-pin power cable for RTX GPUs that aims to tackle connector burning. While first introduced at CES this year, the GPU Shield requires compatible power supplies to operate. Cooler Master did announce the MWE Gold V4 series for the GPU Shield, but it hasn't been out yet. However, it appears that the power […]
As smartphone demand starts to wane due to the memory crisis, companies have been forced to adjust their shipment requirements for a multitude of components, including OLED panels. As a result, this problem has branched out to the entire industry, as display manufacturers are feeling every bit of pressure due to the DRAM shortage. According to the latest statistics, OLED shipments for the first quarter of 2026 fell by 12 percent, but since there’s no reason to halt smartphone production completely, Korean firms continue to benefit. Chinese OLED manufacturers like BOE have created a market for themselves amid the DRAM […]
A few days ago, alongside its quarterly financial report, Sony revealed that it has already embraced AI tools to empower the game development of its own first party studios. More information about this strategy is now available via the Corporate Strategy Earnings Presentation, delivered by Sony CEO Hiroki Totoki and PlayStation President and CEO Hideaki Nishino. Sony's overarching principle is that human creativity must remain central. CEO Hiroki Totoki set the tone plainly: "AI is a powerful tool, but it is not a replacement for artists or creators. It is an amplifier of human imagination and a catalyst for new possibilities". PlayStation […]
It's been more than a year since FromSoftware and Nintendo surprised everyone with the announcement of Elden Ring: Tarnished Edition, a Nintendo Switch 2 specific version of the award-winning open world action RPG that was revealed alongside the console itself. The game was supposed to launch in 2025, but got delayed to 2026 because the developers needed more time to optimize its performance on the weaker system. Now, though, it may be very close to launch, at least according to Canadian retailer PNP Games, which has listed it for an "estimated ship date" of July 10. For the record, that […]
JetMeAway is a UK travel scout focusing on "Life, Not Just Lodging." It compares flights, hotels, packages, car hire, eSIM data, insurance, and activities across 15+ providers like Expedia, Trip.com, Aviasales, and Klook. It adds neighbourhood-level Scout Reports covering morning rituals, wellness, privacy hotels, and local intel for over 30 destinations. The service is free with no markups and prices locked at booking. Native iOS and Android apps launched in May 2026.
SchemaGen is a Schema Delivery Network that lets SEO teams deploy, update, validate, and monitor structured data across entire websites from a centralized dashboard. Add a one-line SDK to push JSON-LD to production in milliseconds while bypassing CMS logins and developer queues. Use real-time validation against schema.org, monitor uptime and schema health by URL, and connect Google Search Console to tie deployments to performance. Manage multiple domains and clients, collaborate with teams, and scale schema operations across WordPress, Shopify, and custom sites.
American educational technology company Instructure, the parent company of Canvas, said it reached an "agreement" with a decentralized cybercrime extortion group after it breached its network and threatened to leak stolen information from thousands of schools and universities.
In an update shared on Monday, the Utah-based firm said it "reached an agreement with the unauthorized actor involved in
OpenAI has launched Daybreak, a new cybersecurity initiative that brings together frontier artificial intelligence (AI) model capabilities and Codex Security to help organizations identify and patch vulnerabilities before attackers find a way in using the same issues.
"Daybreak combines the intelligence of OpenAI models, the extensibility of Codex as an agentic harness, and our partners across
Anthropic has ignited debate after suggesting science fiction stories about rogue AI may unintentionally shape how modern AI systems behave under pressure.
Outage tracker sites Downdetector and IsDown have collected thousands of user reports from mid-afternoon Tuesday, Sydney time — though the search giant has yet to confirm any issues.
Intel CEO confirms planned Intel/Nvidia products after giving Jensen Huang an Honorary Doctorate Intel CEO Lip-Bu Tan has confirmed that Intel is continuing to collaborate with Nvidia on “exciting new products”. This was after Lip-Bu Tan placed a Doctoral Hood on Nvidia’s Jensen Huang, who has received a Doctorate in Science and Technology from Carnegie […]
AAEON, a leading provider of edge AI platforms, today announced the release of the BOXER-8651AI-PLUS and BOXER-8652AI-PLUS, two embedded AI systems powered by NVIDIA Jetson Orin NX module with Super Mode support. The two systems follow the release of the BOXER-8653AI-PLUS back in February 2026, and complete AAEON's BOXER-865xAI-PLUS series.
Designed to provide users across market segments with the enhanced software stack, greater power consumption flexibility and performance optimization offered by Super Mode with NVIDIA JetPack 6.2 SDK, BOXER-865xAI-PLUS series PCs offer up to 157 TOPS of AI performance. The primary differences between the three systems are their form factors and the functions they offer, which in turn influence the types of deployment scenarios AAEON has positioned them for.
vizz.fm turns your audio into real-time visuals in the browser. Connect a mic, upload files, paste a stream URL, or capture system audio, then pick from dozens of reactive visualizers and fine-tune colors, speed, intensity, and sensitivity. You can layer post-processing effects like kaleidoscope and bloom, save presets, and run full-screen for performances. Capture with OBS for streams or record synced exports for content. It’s free with no downloads or sign-up required.
OpenPostern monitors third-party vendors and alerts you to real, actionable risks. It pulls daily data from NVD and CISA KEV, checks SSL/TLS certificates and DNS/HTTP security, and scans security news with AI to find issues affecting your exposure. It combines signals into a 0–100 vendor risk score with clear next steps. You can start in minutes by searching its vendor catalog—no integrations or security team needed. Designed for SMBs, it filters noise so you only act when a vendor issue demands attention.
Chaindoc is an e-signature platform with built-in KYC identity verification, payment collection, and blockchain audit trails all in one workspace. Instead of using separate tools for signing, KYC, and payments, teams can handle the full contract lifecycle from one place.
Signatures comply with eIDAS and ESIGN Act standards and are backed by ISO 27001 and SOC 2 certifications. Every signed document has a blockchain-anchored audit trail that is timestamped, hashed, and independently verifiable. It is built for businesses, freelancers, and remote teams needing contracts and payments to work together without friction.
Apple on Monday officially released iOS 26.5 with support for end-to-end encryption (E2EE) to Rich Communication Services (RCS) in beta as part of a "cross-industry effort" to replace traditional SMS with a more secure alternative.
To that end, E2EE RCS messaging is rolling out to iPhone users running iOS 26.5 with supported carriers and Android users on the latest version of Google Messages.
Right now, every AI model you've ever used works the same way. You talk, it listens. It responds, you listen. Thinking Machines is trying to change that by building a model that processes your input and generates a response at the same time, so it's more like a phone call than a text chain.
Stellar Blade was a highly popular game when it launched, and even though it took over a year to make it from PS5 to PC, it managed to reach an all-time peak concurrent player count of 192,078 players on Steam alone. With Stellar Blade 2 now out in the open and well on its way to an expected 2027-2028 expected launch window, the game's developer, ShiftUp, has officially addressed its launch strategy for the sequel in its Q1 2026 earnings report. There are two major upcoming changes to the publishing strategy for Stellar Blade 2.
Specifically, ShiftUp has confirmed that it will likely be self-publishing Stellar Blade 2, and the Korean game studio is also suggesting that it will shift to a multiplatform launch, instead of the previous timed PS5 exclusive, with the goal of reaching "a broad global audience from day one." It was revealed in previous hints from the game studio that it would be catering much of the Stellar Blade 2 experience to Chinese players, going so far as to use locations in real-world China for the game's setting. This shift to a cross-platform launch could be part of the same strategy that motivated the studio's push into China. It's not yet clear exactly which platforms will be on the Stellar Blade 2 launch roster, but it's almost guaranteed that the game will launch on PC, PS5, and Xbox Series consoles. The full quote from ShiftUp regarding the launch plans follows.
A deal between Intel and Apple could lead to higher demand for chip manufacturing and bonding machines, suggests a report from Bank of America. Media reports have suggested that Apple and Intel have signed an agreement through which some of Apple's chips would be made by Intel. As of now, Apple is believed to procure its chips from Taiwan's TSMC, and following the reports, BofA is out with some fresh estimates about the deal's value and its impact on the chip manufacturing equipment industry. Intel Could Order As Much As €4.6 Billion Worth Of Machines From ASML In Case Of […]
It was recently revealed that Forza Horizon 6 game files have made their way online ahead of the game's official release, with SteamDB reporting early on May 11 that the game's "file list appeared on SteamDB because someone (could be someone else) uses our token dumper" to upload the information. SteamDB postulates that it was a "reviewer or similar" who leaked the game. Playground Games, the developer behind the Forza Horizon series has quickly responded to the game leak, addressing the community directly with consequences for anyone caught with the leaked files and denying any involvement in the leak, which was previously thought to have been as a result of a glitch in the Steam preloading system. According to Playground, the Forza Horizon 6 build leak "is not the result of a preload issue," echoing SteamDB's statement on the matter. Meanwhile, PC players who paid full price for the game, $69.99 or up to $119.99 for the Deluxe Edition, are still unable to preload the game ahead of its official May 19 launch, according to discussions on Steam forums.
However, unlike the rather calm response issued by Capcom when Resident Evil: Requiem's narrative leaked ahead of launch, Playground Games is also "taking strict enforcement action" against anyone accessing the build. The action in question will be franchise-wide and hardware bans, meaning there is a risk associated with playing the pre-release leaked version of the game. These threats have not seemed to deter some, with some players going so far as to post their game reviews based on the build on sites like Reddit. Repackers have also already been hard at work posting their repackaged versions of the leaked game to forums like r/CrackWatch. There may also be workarounds for hardware bans, but many in the aforementioned Reddit post have mentioned that they will simply play the game offline to avoid the hardware bans. Testing for TechPowerUp's in-depth performance review of Forza Horizon 6 has been running since last week and the article will go live on May 14 when the review embargo ends.
WriteHybrid provides an AI humanizer that transforms AI-generated text into natural, human-sounding writing while preserving meaning and readability. It serves students, researchers, bloggers, and marketers who want content that passes major AI detectors such as GPTZero, Turnitin, Originality.ai, Copyleaks, and more. The platform offers generous word limits, multiple rewrite tones, priority processing, and team access, with secure, non-retained processing and a 500-word free trial.
Seeker helps you find roles that fit your actual background even when the job title isn't obvious. Upload your resume and Seeker compares it against 160,000+ live openings to surface jobs where your skills, experience, and career path match.
For each match, Seeker explains why the role fits, what skills connect, any gaps that might hold you back, and salary data when available. You can see your top matches free in under 90 seconds, then create an account to unlock more results and save your analysis.
BinderDex is an iPhone app for tracking your Pokémon card collection before prices change. View instant portfolio value, top cards, and performance at a glance. Save grails and follow a focused watchlist so you can act faster without clutter.
The Entertainment Software Association (ESA) has come out against California bill AB 1921, a state bill that would compel developers to offer remedies before deactivating servers for online games. Stop Killing Games has been fighting this battle for the last couple of years and was quick to condemn the ESA's position.
Aera is an AI running coach that builds your training through real conversation, like the first session with a human coach. It listens to your context such as sleep, fatigue, and schedule, rebalances your week as life unfolds, and delivers a real debrief after every key session. Unlike plan-generators that lock a static schedule, Aera gives advice and sometimes pushes back, but you always have the final say. Workouts sync to Garmin and Apple Watch; activities flow back from Strava, Garmin Connect, and more. Built by a runner, for runners who want coaching, not templates. Currently in open beta, free.
HeyNews is an AI newsletter writer for operators on beehiiv, Kit, Substack, Ghost, Mailchimp, and Medium. It reads your past issues, learns your tone and signature phrases, pulls stories from your sources (RSS, blogs, social profiles, Reddit, Chrome extension), scores them against your audience, and drafts your next issue in your voice. Smart Select picks the right stories per section. You review and send from your platform. HeyNews never auto-publishes.
Different edition types get different writers, so a Monday deep dive and a Friday roundup keep their own style. Plans from $99/month with a 14-day free trial. Built by a two-person team that uses it for our own newsletter.
Some of the positions focus on AI-native development, data engineering and analytics, cloud-based engineering, and agent and model development as well as prompt engineering and new AI workflows.
After taking a stake in Intel, the Trump administration seems to have taken upon itself the responsibility of filling Intel's order book, be it the enthusiastic courting of Apple's Tim Cook with anecdotes of the "tens of billions of dollars" that the US government has recorded in gains over the past few months as Intel shares surged, or pressuring Tesla to now abandon TSMC in favor of Intel's Arizona fabs. Tesla is reportedly facing concerted pressure from the Trump administration to move the fabrication of its AI6.5 chips from TSMC to Intel Back in April, while discussing the taping out […]
AutoSubtitles is a browser-based AI subtitle generator that helps creators make more engaging and accessible video content with accurate subtitles and animated captions. Built for social media videos, podcasts, online courses, marketing content, and more, the platform makes it easy to create polished, professional captions in seconds without complicated editing software. Creators can generate subtitles in 20+ languages, customize styles with animated presets and branding tools, and export ready-to-post videos directly from the browser. AutoSubtitles is designed to increase watch time, improve retention, and streamline video workflows for modern creators and teams.
StackScan shows you what powers any website and helps you find others built the same way. Enter a domain, technology, or topic to see the tools, frameworks, and services in use, with options to filter and export results. Search across 50,000+ technologies and hundreds of millions of websites. Refine by country, TLD, or stack combinations to get relevant results. You can also upload domain lists and enrich them with detailed tech data and additional attributes. Whether you’re researching markets, validating ideas, or building targeted lists, the goal is simple: give you structured, usable data without unnecessary friction.
VirtualBackgrounds generates realistic, on-brand video call backdrops for Zoom, Google Meet, Microsoft Teams, and Webex. Upload your logo and colors, choose refined office styles and lighting, and get high-resolution backgrounds in seconds.
It was recently leaked that Xbox Game Pass would likely become part of bundle deals with the likes of Netflix and potentially other partners, and, as per a recent announcement by both Discord and Microsoft, one of those partners is Discord. The occasionally controversial gaming-first communications platform will now include Game Pass with its paid Nitro subscription service. The Xbox Game Pass subscription included with Nitro is a slightly cut-back version of Xbox's service—Discord calls it a "starter edition"—and it offers "50+ PC and console games." Game Pass is also only included on the full-fat $9.99 version of Nitro, not Nitro Basic, although that's likely still a deal for some PC gamers, depending on taste.
The Nitro plan included with Game Pass has more severe limitations, though, the most notable of which is the lack of online multiplayer on consoles and a 10-hour monthly limit on cloud game streaming. Game Pass will also be directly integrated into the "Now Playing" statuses on Discord. Nitro subscribers will be able to launch Game Pass games directly from Discord—likely by first launching the Xbox app—if they see a game their friend is playing and want to join in. Discord Nitro users will also now have access to discounts of up to 30% on Logitech G, SteelSeries, and KontrolFreak products as of the new Nitro update, which is rolling out to Nitro users in waves "over the coming weeks."
Apple has now publicly rolled out the iOS 26.5 update along with a host of other software updates for its sprawling ecosystem of devices, including iPadOS 26.5, watchOS 26.5, tvOS 26.5, visionOS 26.5, HomePod Software 26.5, and macOS Tahoe 26.5. The Apple iOS 26.5 update is a hefty file, one that is big on bug fixes but light on material feature upgrades Apple has now released the 11.98GB iOS 26.5 update file, bringing new wallpapers along with 2 feature upgrades: Elsewhere, the update brings fixes to over 50 security vulnerabilities in iOS 26.5 alone. Did Apple use Clause Mythos to […]
Zyphra has partnered with AMD to launch its brand new open-source AI platform that rivals DeepSeek & is based in the US, all powered by MI355X GPUs. Zyphra Cloud - The DeepSeek of China Is Here & It Is Powered By An All-AMD Powerhouse With 15MW of Compute Through MI355X & Expansion To Future GPUs The Zyphra AI Cloud platform is an inference-optimized service for frontier open-weight models such as DeepSeek V3.2, Kimi K2.6, and GLM 5.1. The platform combines custom kernels, novel long-context inference algorithms, and advanced parallelism techniques to deliver high-throughput, low-latency AI performance, perfect for agentic, deep […]
TSMC’s slightly advanced 2nm ‘N2P’ process has been reported to be utilized by Qualcomm and MediaTek this year, as both companies seemingly want to obtain an edge over Apple’s A20 and A20 Pro. The advantage of moving to an improved node is that these Android chipset manufacturers can target a higher clock speed for increased single-core and multi-core performance. The drawback is that shifting to this technology can risk mass adoption from smartphone makers due to the major cost increases. The first 2nm chipsets from Qualcomm and MediaTek could cost 20 percent more than current SoCs, but it’s likely that these […]
The Samsung Pro 990 SSD is enjoying discounts on its 1TB, 2TB, and 4TB models on Amazon, giving hardcore PC gamers a chance to upgrade their storage space and cut down on loading times for less.
It seems as though Valve is working on making the launch of the Steam Machine and Frame go down more smoothly than the Controller, according to a new Steam update that has been spotted by a Reddit user, u/pepeizq on r/SteamMachine, Valve will start the Steam Machine with a 512 GB base model and top it off with a 2 TB model. There are four total Steam Machine SKUs (referred to as 1629460, 1629458, 1629446 and 1629447 in the code), so there are likely other configurations between the 512 GB version and the 2 TB version—likely controller bundles and perhaps a barebones model for those with a pile of SSDs in a desk drawer somewhere. Additionally, in order to avoid the early supply and scalping issues faced by Valve's Steam Controller, the Steam Machine will launch with a reservation system right out the gate. Similarly, the Steam Frame will likely ship with 256 GB or 1 TB of storage.
From the code in the update, it looks like the same reservation limitations will apply to the Steam Machine and Steam Frame, meaning users will only be able to reserve one item per account, and they must have an active, pre-existing Steam account in good standing in order to make a reservation. More interestingly, the code also makes reference to a "PSULessModel," which may refer to a Steam Frame model without an external PSU—for those who plan to charge the built-in 21.6 Wh battery with a regular USB-C PD charger or those who mostly plan to use the device tethered. It doesn't seem reasonable that Valve would sell a PSU-less Steam Machine, since that has a built-in PSU that is necessary to function.
Intel plans to reintroduce on-package memory in the future, with the "Razor Lake-AX" potentially being the product to carry this feature. This could be a successor to the "Nova Lake" generation, expected to arrive in late 2026. The last time Intel used on-package memory was with the "Lunar Lake" Core Ultra 200V series of CPUs, which included LPDDR5X-8533 memory in a single package alongside the CPU, GPU, and I/O die. Intel had previously stated that future CPU generations after "Lunar Lake" would use off-die memory, as sourcing and integrating additional memory modules in its SoCs is challenging, despite having technologies like EMIB and Foveros 3D to support integration. However, this decision seems to be reconsidered, as Intel is reportedly planning to integrate memory back on-package with "Razor Lake-AX."
Intel's AX variants of SoCs have long been rumored to offer significant integrated graphics capabilities to handle demanding graphics workloads. This lineup is intended to compete directly with AMD's "Halo" series, which includes "Strix Halo," "Gorgon Halo," and other future revisions like "Medusa Halo." Intel aims to achieve excellent iGPU performance, bundled with substantial integrated memory such as LPDDR5X or the upcoming LPDDR6 memory. Eventually, Intel might reintroduce HBM memory, similar to what it did with "Kaby Lake G," but we are still awaiting more details from rumors and leaks. Amidst a significant memory shortage in the PC gaming world, Intel would likely face challenges in acquiring sufficient DRAM stock. However, by the time "Razor Lake-AX" arrives in the coming years, the situation could be quite different.
Hints about the new reservation system were found in the latest Steam update files released last week. Redditor Pepeizq, who spotted the reservation system code, also found references to at least four Steam Machine packages and two Steam Frame packages. The code also mentioned the existing Steam Controller and Steam...
Electric bikes were responsible for nearly a third of all calls – 520, to be exact – in the UK last year. Unsurprisingly, retrofitted models were involved in more incidents compared to those that shipped with batteries from the factory. For comparison, there were only 149 calls for ebike fires in 2022.
Korean customs export/import data has been updated, showcasing the massive DRAM & NAND price surge that will affect global memory and SSD markets. NAND & DRAM Demand Has Swollen To Record Levels & Korean Semiconductor Firms Are Earning Big Time Due To Memory & SSD Price Surges The latest data from the Korean customs import/export department, specifically focusing on DRAM and NAND segments, has been released. As per the new data, DRAM & NAND demand surge can clearly be seen, which has affected all major tech components, with their prices seeing a massive hike of up to 63% in a […]
After nearly a decade of dormancy, one of Nintendo's most beloved franchises is finally making its comeback. Star Fox was announced during a surprise Nintendo Direct in May 2026 as a full remake of the classic Star Fox 64, and it's coming sooner than anyone expected. Originally released on Nintendo 64 in 1997, Star Fox 64 put players in the cockpit of Fox McCloud's Arwing as he and his team fought to liberate the Lylat system from the exiled scientist Andross. The game previously received a 3DS remake in 2011 (Star Fox 64 3D); then there was Star Fox Zero, released for the Wii U in […]
Galaxy S26 Ultra may not have the biggest battery capacity or those ultra-sized sensors, or a beefy active cooling solution that includes a noisy fan, but what it does have is a combination of all the strengths of current-generation flagships fused into a single device, making it an all-round package. The best thing about this smartphone is that you can grab it for up to $222 off on Amazon, with the discount applicable on the 512GB storage version and the White finish. Fortunately, other Galaxy S26 Ultra variants have also received a price reduction. Smaller storage options and different colors […]
Unknown Worlds has opened up pre-orders for Subnautica 2 as the game surpasses 5 million wishlists on Steam ahead of its early access launch later this week on May 14, 2026. Subnautica 2 has reportedly been the most wishlisted game on Steam, and it will almost definitely be one of the biggest launches of 2026 before the end of the year. Even though, technically, it probably should've been one of the biggest releases of 2025 before a legal battle between Unknown Worlds' parent company Krafton and the co-founders of Unknown Worlds overshadowed the game for the past year. After that […]
toflow lets B2B sales teams run outbound with AI agents connected to Claude via MCP. From a single conversation, you can build targeted lead lists, enrich contacts with verified emails and phone numbers, create multi-channel sequences, and trigger smart follow-ups across email, LinkedIn, and WhatsApp. A Chrome extension captures prospects from LinkedIn, Apollo, and more, while shared pipelines, reply tracking, and CRM sync keep your team aligned and deals moving.
Autonomous Accounting automates bookkeeping for Canadian SMBs. Upload receipts, invoices, and bank statements (PDF, image, CSV). AI extracts amounts, vendors, dates, and taxes with deterministic cross-verification. A 4-pass matcher (strict / FX-aware / split-aware / LLM) reconciles documents to transactions. Output is a CRA-compliant Audit Binder — ZIP, 6-year retention, every ledger entry hyperlinked to source. One tier: $12 CAD/month or $99/year. No per-receipt fees. Encrypted storage, zero-retention LLM, no human reviewers. Built solo by Martin Liu in Vancouver. 14-day free trial.
Google is set to automatically link Google Ads accounts with associated YouTube channels — according to communications sent to multiple advertisers — tightening the connection between video engagement and ad performance.
What’s happening. Advertisers have received notices that, from June 10, 2026, Google Ads accounts that aren’t already linked to a YouTube channel will be automatically connected.
The update removes the need for manual linking and ensures advertisers can access video engagement data and targeting features by default.
Why we care. Linking a YouTube channel unlocks deeper insights and more advanced targeting options — something many advertisers either overlook or delay setting up.
By automating the process, Google is effectively making video data a standard part of campaign optimisation.
Zoom in. Once linked, advertisers can access organic video metrics, including view counts, directly within Google Ads.
They can also build audience segments based on how users interact with their YouTube content — from video views to channel engagement.
What else. The integration allows advertisers to track “earned actions,” such as subscriptions or additional views driven by ads, and use those engagements as conversion signals.
That creates a clearer picture of how video campaigns influence user behaviour beyond just clicks.
What to watch. How advertisers adapt their measurement strategies once organic and paid video data are combined, and whether this leads to broader use of engagement-based conversion tracking in campaigns.
Bottom line. Google is making YouTube data harder to ignore — turning automatic linking into a default step for better targeting, measurement and performance.
First spotted. Several advertiser reported getting the comms from Google, including Founder of JXT Group, Menachem Ani, founder of PPC News Feed Hana Kobzová, and PPC Specialist Arpan Banerjee.
Checkmarx has confirmed that a modified version of the Jenkins AST plugin was published to the Jenkins Marketplace.
"If you are using Checkmarx Jenkins AST plugin, you need to ensure that you are using the version 2.0.13-829.vc72453fa_1c16 that was published on December 17, 2025 or previously," the cybersecurity company said in a statement over the weekend.
As of writing, Checkmarx has released
The Google Store is running a promotion that gives you the chance to get the new Fitbit Air for free when you trade in your current smartwatch or fitness tracker.
The longer that Richard Gadd's new TV show continues, the more Ruben makes me feel sick. But when does Half Man episode 4 drop on HBO Max and BBC iPlayer?
AMD’s Radeon RX 9050 8GB GPU leaks It looks like AMD is planning to launch a new, lower-end, RDNA 4-based graphics card. This new GPU uses the same silicon as AMD’s Radeon RX 9060 XT, but runs at much lower clock speeds and has a lower power limit. This makes this GPU ideal for low-power […]
Forza Horizon 6 leaked early and cracked builds are online, but Xbox and Playground Games say you're getting a hardware ban if you're caught playing them.
Several Razer gaming accessories themed after the classic Pokémon Gengar, including a gaming headset, gaming mice, and a mouse pad, are all enjoyable limited-time bargains at Amazon.
Login
We’re committed to building AI-driven protections and collaborating with industry and governments to keep you safe from scams and fraud. 
Google is launching Gemini in Chrome, including auto browse, to deliver a new agentic experience on Chrome for Android. 
We’re introducing Googlebook, a new category of laptops designed for Gemini Intelligence and perfectly in sync with your Android phone. 
New features on Android 17 include an optimized Instagram experience, advanced editing tools and Adobe Premiere. 
This new wellbeing feature helps stop doomscrolling so you can use your phone with more intent. 
Android Auto and cars with Google built-in are getting upgrades. Drivers can look forward to a rich new experience, premium entertainment and a more capable Gemini. 
With added depth and rich details, Noto 3D emoji make it easier to say what words alone can miss. 
The latest Android updates let you share files and switch devices with ease and keep your chats secure. 
At the Android Show 2026, we introduced Gemini Intelligence, proactive new AI features on Android. 
Your front-row seat to the latest breakthroughs on the world’s most popular operating system. 
