AI news with trend context.

GPT-Live is not just a smoother ChatGPT Voice. The important product move is realtime interaction in front, delegated reasoning in the background.

Muse Spark 1.1 is not just another Meta model launch. The useful signal is that Meta is packaging long context, tool use, subagents, computer use, and an OpenAI compatible API as an agent control layer.

The Antigravity product teams were on-site filming this exact transition, capturing how developers move from vibe coding to production-grade deployment at the edge

We’ve expanded Claude’s context window from 9K to 100K tokens, corresponding to around 75,000 words!

Update: Now available on Google Cloud's Vertex AI (Aug 26, 2025) Claude Sonnet 4 now supports up to 1 million tokens of context on the Anthropic API—a 5x increase that lets you process entire codebases with over 75,000 lines of code or dozens of research papers in a single reques

The Antigravity product teams were on-site filming this exact transition, capturing how developers move from vibe coding to production-grade deployment at the edge

With 100K context windows, you can: Digest, summarize, and explain dense documents like financial statements or research papers Analyze strategic risks and opportunities for a company based on its annual reports Assess the pros and cons of a piece of legislation Identify risks, t

Update: Now available on Google Cloud's Vertex AI (Aug 26, 2025) Claude Sonnet 4 now supports up to 1 million tokens of context on the Anthropic API—a 5x increase that lets you process entire codebases with over 75,000 lines of code or dozens of research papers in a single reques

If you've trained large models across many machines, you already know the answer: the communication times out, every worker exits, and you re-launch the whole job from the last checkpoint

We engaged a leading national security expert, David Kris, to help facilitate the process and provide his independent judgment, held listening sessions across the company, and engaged employees representing a range of teams from research and safety to policy and government partne

Chinese AI developer MiniMax is working on a new large language model with 2.7 trillion parameters. MiniMax plans to release the model as open source. The article Chinese AI startup MiniMax plans to open-source a 2.7 trillion parameter model later this year appeared first on The Decoder .

Kevin Weil's new role at Stoke Space suggests reusable rockets are the next hot thing in Silicon Valley.

Meta's Superintelligence Labs ships Muse Image, its first image generation model. Like OpenAI's GPT Image 2, it works as an agent, using tools like code execution and web search to refine its own results. A controversial @-mention feature lets users generate images of other people using their public Instagram photos without consent. The opt-out model is likely to collide with the GDPR and the EU AI Act. The article Muse Image is technically impressive, but Meta's use of Instagram photos raises q

OpenAI is launching GPT-5.6 on Thursday after the U.S. government lifted the initial release ban following additional testing. According to OpenAI, the Sol model outperforms Anthropic's Claude Mythos 5 in the coding benchmark while costing about half as much. Binding standards for future model approvals are still lacking. The article OpenAI's GPT-5.6 launches Thursday after a delay forced by the U.S. government appeared first on The Decoder .

ZML, a hot French AI startup endorsed by Turing Award winner Yann LeCun, has now released ZML/LLMD, software that could make running AI less costly.

The Copilot usage metrics API now reports two additional code-review velocity metrics for each AI adoption phase, extending the adoption phase cohorts fields available in the enterprise and organization reports.… The post Add review cycles and time to adoption phases in the usage API appeared first on The GitHub Blog .

On July 1, 2026, we announced Kimi K2.7 would be available to Copilot Pro, Pro+, and Max plans. The model is now additionally available on Copilot Business and Copilot Enterprise… The post Kimi K2.7 now available for Copilot Business and Enterprise appeared first on The GitHub Blog .

The new image-generating model has numerous use cases, including advertising, decorating and creator-based opportunities.

The new image-generating model has numerous use cases, including advertising, decorating and creator-based opportunities.

Hugging Face Blog surfaced From Hugging Face to Amazon SageMaker Studio in one click. The useful question is not whether it is hot, but what it changes for a team shipping real AI workflows.

Open-source models’ success isn’t coming at the expense of frontier labs. Instead, they each seem to capture two phases of the same life-cycle.

This morning I released sqlite-utils 4.0 , the 124th release of that project and the first major version bump since 3.0 in November 2020. In addition to some small but significant breaking changes (described in this upgrade guide ), this version introduces three major features: database migrations , nested transactions (via a new db.atomic() method), and support for compound foreign keys . Database schema migrations using sqlite-utils Schema migrations define a sequence of changes to be made to

Microsoft is replacing AI models from OpenAI and Anthropic with its own MAI models in products like Excel and Outlook. Tens of thousands of queries per week already run through them. AI chief Mustafa Suleyman wants to "ultimately eliminate" the cost of external models. For Copilot customers, that could mean less performance for the same price. The article Copilot goes cheap as Microsoft phases out OpenAI and Anthropic models to cut costs appeared first on The Decoder .

Cohere has released Transcribe Arabic, an open-source model for Arabic speech recognition that the company says outperforms Whisper and OmniASR on dialects, code-switching, and bilingual Arabic-English speech. The 2-billion-parameter model is available on Hugging Face under the Apache 2.0 license. The article Cohere Transcribe Arabic is an open-source model built for Arabic's toughest transcription problems appeared first on The Decoder .

Enterprise admins can now create cost center user-level budgets directly in the billing UI where you manage cost centers and budgets. This feature is available for GitHub Enterprise Cloud. This… The post Per-user budgets for cost centers in the billing UI appeared first on The GitHub Blog .

Anthropic is rolling out its AI agent Claude Cowork to mobile and web. Until now, the feature was limited to the desktop app. The agent keeps working in the background even when the laptop is closed and pings users on their phone when it needs a decision. The move blurs the line between Chat and Cowork even further. The article Anthropic's Claude Cowork AI agent is now available on mobile and web appeared first on The Decoder .

To help you understand ownership and impact of a leaked secret, GitHub secret scanning surfaces enriched metadata for supported secret types. Extended metadata checks are now generally available, including support… The post Secret scanning extended metadata and multipart validation appeared first on The GitHub Blog .

Algorithms & Theory

We ran an experiment in 10 major US cities to demonstrate the effectiveness of targeted low-cost routing interventions in improving overall traffic conditions

We ran an experiment in 10 major US cities to demonstrate the effectiveness of targeted low-cost routing interventions in improving overall traffic conditions

Anthropic’s Claude Cowork is now available on web and mobile for Max subscribers. Until now, Cowork largely lived on a user’s laptop. With the update, users can start a task from their desk, get status updates on their phone, and pick up the finished output later — even if their laptop is closed.

According to Reuters, Chinese authorities are looking into restricting foreign access to the country's most powerful AI models. Alibaba, Bytedance, and Z.ai would all be affected. The move means both superpowers now treat AI as a strategic asset. For Europe, the convenient shortcut of relying on cheap Chinese open-source models could close much faster than expected. The article China eyes export curbs on its top AI models, and Europe is caught in the middle appeared first on The Decoder .

Hugging Face Blog surfaced Hugging Face Models on Foundry Managed Compute. The useful question is not whether it is hot, but what it changes for a team shipping real AI workflows.

You can now restrict who can dismiss pull request reviews directly in GitHub repository rulesets. This capability is generally available and gives you precise control over who can clear an… The post Restrict who can dismiss reviews in rulesets appeared first on The GitHub Blog .

The company just raised $7 million in seed funding, and is launching its app for iPhone and Android on Tuesday.

Chinese AI models are gaining ground with US companies because they cost far less than systems from OpenAI and Anthropic, CNBC reports. The article Chinese AI models regularly pass 30 percent on OpenRouter as cost gap widens appeared first on The Decoder .

Chinese startup Deepseek is building its own AI chip, Reuters reports. The article Deepseek is designing its own AI chip appeared first on The Decoder .

Forterra has deployed more than 100

Employees often need to synthesize large volumes of context and turn technical information into clear decisions, documents, and member-facing guidance

In one reconciliation instance, AP+ teams used Codex to trace a subtle timestamp inconsistency across system logs and reconciliation data, reducing days of manual investigation to minutes

hours saved each week by 77% of surveyed employees using ChatGPT of surveyed employees report improved creativity or work quality to build working simulations with Codex, down from what could previously take days to weeks investigation time for complex reconciliation issues using

See how Australian Payments Plus uses ChatGPT Enterprise and Codex to move faster through payments complexity. AP+ saves time, improves quality, and keeps human judgment central.

Official Hugging Face source signal with builder-relevant workflow implications.

tencent/Hy3 New Apache 2.0 licensed model from Tencent in China: Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. Today, we introduce Hy3, which outperforms similar-size models and rivals flagship open-source models with 2-5x parameters. It also shows significa

An AI agent carried out the technical execution of a real-world ransomware attack for the first known time, but new details show a human still chose the victim, set up the infrastructure, and supplied stolen credentials — meaning it wasn't quite the fully autonomous cybercrime debut that last week's headlines suggested.

SK Hynix is experiencing a boom credited to AI. It will ride that to a multi-billion dollar US IPO, expected to take place on Friday.

Distributed AI training is notoriously fragile because losing a single machine typically crashes the entire multi-node job, forcing a time-consuming, full-workload infrastructure restart. To address this, Google’s JAX ecosystem utilizes elastic training via Pathways, which converts a hardware failure into a catchable Python exception so the running process can survive. When an unplanned failure occurs, the system automatically replaces only the broken worker, restores the last viable checkpoint

"The reality is, when you're optimizing for production, you start looking at a price/performance," Guillermo Rauch tells TechCrunch.

Cloudflare is giving all customers granular AI bot controls. Site owners can now manage Search, Training, and Agent bots separately instead of blocking them all at once. Starting September 15, 2026, Training and Agent bots will be blocked by default on ad-supported pages.

Security firm Sysdig describes an extortion attack where a language model broke in on its own, stole credentials, and destroyed databases. No human appeared to be at the controls.

Release: sqlite-utils 4.0rc3 I hoped to release sqlite-utils 4.0 stable this weekend, but as I worked through the backlog of issues and PRs with a combination of Claude Fable 5 and GPT-5.5 the changeling since rc2 kept getting bigger . The biggest new feature is support for introspecting and creating compound foreign keys - a feature that involves a subtle breaking change to table.foreign_keys and hence needed to land for the 4.0 stable release. sqlite-utils also now follows SQLite's convention

Official source signal from Anthropic News Sitemap with builder-relevant workflow implications.

Claude's 1M context window is useful for long-document review and corpus analysis, but builders should test cost, latency, and review quality before replacing RAG.

Official source signal from Claude Blog Sitemap with builder-relevant workflow implications.

Official source signal from Anthropic News Sitemap with builder-relevant workflow implications.

Official source signal from Anthropic News Sitemap with builder-relevant workflow implications.

Official source signal from Anthropic News Sitemap with builder-relevant workflow implications.

The open-source Genkit framework has introduced the Agents API, a full-stack tool designed to simplify the complex plumbing of conversational AI by packaging message history, tool loops, and streaming into a single interface. The API supports flexible, server- or client-managed state persistence—allowing for advanced workflows like history branching, long-running detached tasks, and multi-agent coordination—while seamlessly connecting backends to frontends via a unified wire protocol. Currently

Building AI agents often leaves developers uncertain if prompt tweaks to fix single errors will accidentally cause widespread regressions in production. To bridge this gap, Google has introduced a new developer skill for coding agents that automates a five-stage evaluation flywheel: preparing data, running inference, grading with adaptive AutoRaters, analyzing failure clusters, and executing targeted optimizations. Running continuously against production traffic or on-demand via synthetic scenar

The Google Cloud Workbench Notebooks extension for VS Code has officially launched, allowing developers to connect their local IDE to scalable, cloud-based Jupyter environments. This integration streamlines the machine learning lifecycle by eliminating context switching and providing direct access to high-performance Google Cloud infrastructure. To support transparency and community-driven innovation, the newly released extension is fully open-sourced and available on GitHub and the VS Code Mark

Answering the questions of "why we built ADK 2.0". This explains the rationale, some of the features, and why a developer should consider upgrading. This will be published the day after ADK go 2.0 launches.

Official Hugging Face source signal with builder-relevant workflow implications.

These may be the last days of Amazon’s Mechanical Turk.

A Google Deepmind developer ported the 2003 real-time strategy game "Command & Conquer: Generals Zero Hour" to iPhone and iPad using Anthropic's Claude Code. The first build took 40 minutes. The full source code is on GitHub.

Baidu's Unlimited OCR reads dozens of document pages in a single pass, where previous systems topped out at about ten. A modified attention mechanism keeps memory use flat no matter how many pages the model processes. It currently holds the top spot on the most important OCR benchmark.

I wrote about the sqlite-utils 4.0rc1 release a couple of weeks ago. Since we only have Claude Fable on our Max subscriptions for a few more days, I decided to see if it could help me get to a 4.0 stable release that I felt truly comfortable about, since I try to keep to SemVer and like my incompatible major versions to be as rare as possible. I started with this prompt, in Claude Code for web on my iPhone: Final review before shipping a stable 4.0 release - very important to spot any last minut

Release: sqlite-utils 4.0rc2 See sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25) .

Building a World Map with only 500 bytes Iwo Kadziela (assisted by Codex) figured out a way to generate a credible ASCII world map using 445 bytes of data: The key trick is to use deflate compression, which is then wired together using this neat snippet of JavaScript. I didn't know you could use fetch() with data: URIs like this: fetch('data:;base64,1ZpLsgIxCEXnrM...==').then( r => r.body.pipeThrough(new DecompressionStream('deflate-raw')) ).then( s => new Response(s).text() ).then( t => b.inner

Two hundred and fifty years after the signing of the Declaration of Independence, a new commercial asks: What if the Founding Fathers had access to Google Workspace?

As part of an ongoing legal dispute with three Hollywood studios, Midjourney is seeking to compel those studios to reveal how they use AI themselves.

We’ve made three improvements to the Copilot usage metrics API that make its reports more complete and accurate: GitHub Copilot CLI now reports suggested lines of code, users seen only… The post Improved accuracy and coverage in Copilot usage metrics reports appeared first on The GitHub Blog .

We will deprecate Gemini 2.5 Pro and Gemini 3 Flash across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) on July 31st,… The post Upcoming deprecation of Gemini 2.5 Pro and Gemini 3 Flash appeared first on The GitHub Blog .

You can now run GitHub Copilot CLI in GitHub Actions using the built-in GITHUB_TOKEN. This means that you no longer need to create and store a personal access token (PAT),… The post Copilot CLI no longer needs a personal access token in GitHub Actions appeared first on The GitHub Blog .

We're opening the waitlist for our Monetization Gateway, which will allow you to charge for any web page, dataset, API, or MCP tool behind Cloudflare. The charges will settle in stablecoins over the x402 open protocol, with no payments stack of your own to build.

One year after declaring Content Independence Day, a dynamic market for monetized content has officially emerged. In this report, we examine how the rise of autonomous AI agents is upending traditional search referrals and detail the new infrastructure required to support a sustainable web economy.

Search is how we find nearly everything on the web — creators, merchants, answers. AI is rewriting the rules, leaving creators caught between staying discoverable in an agentic era and getting paid for their work. Today we're launching two initiatives to help.

Official Hugging Face source signal with builder-relevant workflow implications.

Official Hugging Face source signal with builder-relevant workflow implications.

Climate & Sustainability

Official Hugging Face source signal with builder-relevant workflow implications.

Data Management

New OpenAI Signals data shows how ChatGPT adoption is growing globally, with users increasing usage, exploring more capabilities, and driving growth across regions and languages.

OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.

Official OpenAI News source signal with builder-relevant workflow implications.

Introducing GeneBench-Pro, a new benchmark testing AI performance in genomics, biology, and scientific research using complex, real-world datasets.

Machine Intelligence

Explore how the GitHub Copilot agentic harness delivers strong results across multiple benchmarks and leading token efficiency, while maintaining flexibility to choose among more than 20 models. The post Evaluating performance and efficiency of the GitHub Copilot agentic harness across models and tasks appeared first on The GitHub Blog .

Algorithms & Theory

Explore how my day as a senior leader looks now that I use 40 automations to help, and learn more about some of my favorites. The post I automated my job (and it made me a better leader) appeared first on The GitHub Blog .

Qubot, our internal Copilot-powered analytics agent, allows any GitHub employee to ask questions about our data in plain language. Here's what we learned as we built it. The post How we built an internal data analytics agent appeared first on The GitHub Blog .