Anthropic’s Sept 14 engineering post says Claude now authors ~80% of its code and CI jobs rose 25x in six months. After three short-lived patches, they redesigned test impact analysis around a journaled in-memory store so listener workers stay horizontally scalable.
Released Oct 28 as @aws/agentcore 1.0.0 on npm, the rebuilt CLI starts faster and lets you work directly with harnesses, runtimes, memory, identity, gateways and payments by ID or ARN, with an interactive shell and harness export. Existing projects move over with agentcore migrate…
Launched Oct 29, it lets you pick up projects running in CodeBuddy IDE or Kimi Code Desktop on your computer, read the chat history, send follow ups or start new tasks from the Marvis mobile app, with changes synced back to the desktop. An anti sleep option keeps the computer awake for long runs, and Tencent says more coding tools will follow…
Released Oct 28, kimi import sessions (or /import sessions ) converts up to 100 Claude Code and Codex sessions from the last 15 or 30 days into regular Kimi sessions in their original project folders, locally and without calling a model or touching the originals. The release also makes Plan mode user only, so the agent can't enter it or auto approve plans on its own (changelog)…
Published Oct 29, the research shows a booby trapped page got Cursor's agent to run a host command (patched Oct 1), and a local HTML file in Codex, VS Code or Claude Desktop could read and exfiltrate files across the disk, with Copilot spoofing the address bar (fixed in 1.1.29). Codex and VS Code were still unpatched at publication, so be careful opening untrusted HTML in their built in browsers (Help Net Security)…
Released Oct 29, the TUI now lets you select and search the transcript by word, line or page with configurable shortcuts, and adds codex queue resume and codex doctor network only . Resumed or forked threads now keep their approval settings and reasoning token counts, so they don't compact early…
Spotted something we missed? Start a thread.
