What shipped & dropped across AI labs, today.
Today
Wed · Sep 2 · 5 posts
Self-hosted machines
Cursor supports self-hosted machines, which let you keep tool execution entirely in your own network. Your codebase, build outputs, and secrets all stay on internal machines running in your infrastructure, while the agent handles tool calls locally. #Dynamic pool scheduling My Machines connects a single laptop or VM to your account for personal workflows. Team pools are named queues of workers for a team or enterprise. Capacity can grow as requests arrive and shrink when workers disconnect, so your self-hosted machines can scale with demand. Pools are not tied to one repository: name the pool, and any available worker can claim the request. Pools can also hibernate idle machines, then restore within a reconnect window when a follow-up arrives, so you don't keep expensive capacity warm just for the next prompt. #Run on your sandboxes Cloud agents can now execute on infrastructure you already use, including from AWS Lambda, Coder, Cloudflare, Daytona, Modal, Namespace, Vercel, and E2B. #Computer use on Linux and Mac Self-hosted workers now support computer use on Linux and Mac. With the right desktop packages, an agent can click, type, take screenshots, and drive the browser. You can watch its desktop or take control from Cursor.
Enterprise-managed settings support any default model
You can now set your preferred GitHub Copilot model as the default for new conversations through enterprise-managed settings. This lets you choose the default model that best fits your workflows.…
4 engineering patterns behind the strongest AI Agents Challenge submissions
The recent Google for Startups AI Agents Challenge revealed that the most successful multi-agent systems rely on foundational software engineering patterns rather than just raw model power. Winning architectures consistently implemented bidirectional MCP for seamless inter-agent communication, async event buses for parallel execution, strict unified validation for model fallbacks, and tiered routing to minimize expensive inference calls. By prioritizing these structural practices over simple linear prompt chains, developers can build more resilient, low-latency, and cost-effective agentic workflows.
Building commerce agents with Claude
We're launching a blueprint to help build commerce agents on Claude. It contains the harnesses, patterns, and guardrails an engineering team needs to get a commerce agent running in days.
A guide to the anatomy of effective commerce agents
The architecture, latency & cost techniques, and eval practices for agents that make it easier to buy and sell online.
Yesterday
Tue · Sep 1 · 7 posts
Proactive cyber defense for governments and enterprises
Introducing Gemini 3.8 Flash and 3.8 Flash Cyber
Claude Fable 5.1 is generally available in GitHub Copilot
Claude Fable 5.1 from Anthropic is now available in GitHub Copilot. The latest model in Anthropic’s Mythos class, Claude Fable 5.1 is designed for long-horizon, autonomous coding and knowledge-work tasks.…
Copilot code review can now approve pull requests
Copilot now tells you when a pull request is ready to approve, and admins can authorize it to sign off on approval. The ability for Copilot to approve is off…
Developing Enterprise Frontier Safeguards with our customers
Introducing agentic video understanding with Gemini
Biosecurity at the frontier
LatchBio evaluated Grok's performance on biosecurity monitoring and adversarial biological tasks. They found that Grok 4.6 detects and refuses dangerous queries more reliably than any other frontier system.
Monday
Mon · Aug 31 · 4 postsSelected GitHub Copilot models deprecated
As of today, September 1, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Note…
Copilot model access update for GitHub Team plans
We have updated how model access is determined for Copilot users who hold seats in more than one organization. To keep billing and governance in sync, your model access is…
Improving our alignment and security efforts
GitHub Copilot in VS Code, August 2026 releases
This changelog covers VS Code v1.132 through v1.135, shipped throughout August 2026. These releases make it easier to organize agent sessions, review changes, and navigate long conversations. Agent Host, the…
Saturday
Sat · Aug 29 · 1 postFriday
Fri · Aug 28 · 3 postsHow Anthropic employees use Claude Tag
Producing customer-ready collateral, compiling weekly issue reports, and running legal review, all where the work already happens.
GitHub Copilot weekly releases — August 24
This week's updates give you more control over how Copilot runs, from team sessions in Slack and Teams to customization across the app, CLI, and your IDE.
GitHub Copilot in Visual Studio — August update
August 2026 brought more control over how GitHub Copilot reasons, which models you use, how teams share specialized agents, and when you ask for a code review. Highlights Here’s what’s…