Daily AI news, sourcedUpdates / Agents & coding
Updates Agents & coding · 325 items · newest issue first · page 2 of 17
AreaAllModelsAgents & codingApps & productsChips & infraResearchPricing & limitsBusiness & fundingPolicy & safetyOther
- Cursor adds Meta's Muse Wonder, which scores 46.1% on CursorBench at default effortOfficialCursorOct 17Agents & coding
- Google DeepMind says four Gemini 4 Argon agents beat Minecraft from scratch in 27 hoursOfficialGoogle DeepMindOct 17Agents & coding
- Claude Code team explains how it reviews agent-written code, with merged PRs doubling and reverts down over 40%OfficialAnthropicOct 17Agents & coding
- OpenAI says Stack Overflow for Agents tripled signups overnight after launching a ChatGPT plugin
- AWS details a nine-stage evaluation framework on Bedrock AgentCore for catching silent agent quality regressions
- Cursor cloud agents can now build shareable canvases, and the Environments API enters beta
- Dualverse AI launches rStation, a research community where AI agents discuss problems and publish reviewed papers
- LangGraph CLI 0.4.36 accepts serverless and dedicated deployment aliases
- Qoder 1.34.0 retires the Quest Window and moves its features into the Editor Window
- OpenCode 1.19.3 lets you configure model reasoning options to generate reasoning variants
- Developer details how open-source code reviewer lgtmaybe runs pull request reviews on a local 27B modelUnconfirmedr/LocalLLaMAOct 16Agents & coding
- Cline Desktop v0.0.47 fixes marketplace plugins, retries interrupted responses and makes Gemini 4 Argon the default Cline model
- OpenCode 1.19.2 keeps 1.x installs on the 1.x line so they are never offered OpenCode 2 as a regular update
- Cline SDK 0.0.94 removes in-process plugins, running them only in worker threads or a subprocess sandbox
- Sarvam ships an MCP server so Claude Code, Cursor and VS Code can build and run Sarvam voice agents
- Harvey launches Legal Work Orchestration to split matters into phases and tasks for agents and lawyers
- OpenRouter launches Armor in beta to block policy-violating agent tool calls before they run
- Google brings Gemini 4 Argon to Antigravity desktop and CLI for AI Pro subscribers, and says 100,000+ Alphabet staff use it monthlyOfficialGoogle AntigravityOct 16Agents & coding
- Anthropic makes Claude Code Review generally available for Team and Enterprise, about 3x faster than the previewOfficialAnthropicOct 16Agents & coding
- Self Labs launches Agent Vault so AI agents can pay and sign in without ever seeing real card numbers or passwords