Claude Code 2.1.277 reads AGENTS.md when CLAUDE.md is missing
Claude Code 2.1.277 now falls back to AGENTS.md when no CLAUDE.md is in the folder, aligning with OpenAI’s agent-instructions format used by Codex and 60k+ repos. Toggle it with /config.
NewsView all
More news
Google Antigravity agent: secrets stay outside the sandbox
Google’s Gemini API docs for antigravity preview 09 2026 describe a managed agent that runs code in a remote Linux sandbox with automatic context compaction at 135k tokens. Network credentials are injected by an egress proxy on allowlisted domains, so tokens never land in the sandbox filesystem or the model’s context…
Kimi K3 now generally available on Amazon Bedrock
Moonshot’s 2.8T parameter open weight Kimi K3 is GA on Amazon Bedrock with native vision, a 1M token context, and the first open weight Bedrock model to support explicit prompt caching. It’s available via US Geo and Global cross Region inference profiles for coding and long agent workflows…
Meta opens Muse connectors so third-party APIs can plug into its agent
On Sept 18 Zuckerberg opened muse.ai/platform for developer connector submissions: bring an API, Meta reviews for functional/security/legal fit, then list in Muse’s directory with Stripe Link for payments. No public SDK, fees, or named launch partners yet…
Hacktron: Claude helped researchers reach OpenAI’s internal GitHub
SiliconANGLE reports Hacktron researchers chained a libheif RCE on OpenAI’s Discourse forum with an SSO misconfiguration, took over employee ChatGPT/Codex accounts, and opened a harmless PR in OpenAI’s private monorepo as proof. OpenAI patched within about 14 hours and paid a $6,500 bounty; Claude Opus 5 helped bypass ASLR after Opus 4.8 stalled…
Cua open-sources CUA-S1-FORMS: 706k-param System One model for forms
Cua released CUA S1 FORMS (Sept 18): a 2.8 MB, 706,048 parameter MIT licensed model that scores fill/check/click/skip options in one pass from extracted document values, then hands execution to Cua Driver. It is the first in a planned CUA S1 family of narrow System One specialists aimed at cutting LLM loops from repetitive computer use workflows…
Spotted something we missed? Start a thread.