lab Claude Code Releases · just now · agents

v2.1.231 fixes MCP OAuth sign-in redirect URI mismatch

from English

Version 2.1.231 addresses an issue where Model Context Protocol (MCP) OAuth sign-in failed due to a redirect URI mismatch.

The update resolves the failure for servers using pre-registered OAuth clients, such as Slack.

This change ensures reliable authentication for users connecting to services with fixed OAuth configurations.

Importance 1/3 Trust 2/3 Claude Code Releases Anthropic AI agents

Read original

blog Simon Willison · 9h ago

Anthropic makes Auto mode the default in Claude Code for Pro, Max, and Team plans

Anthropic is changing Claude Code so that Auto mode becomes the default setting for new sessions on Pro, Max, and Team plans starting August 14th. This shift follows internal adoption at Anthropic and new evaluation data demonstrating improved safety against prompt injection.

lab Claude Code Releases · 11h ago

Claude Code v2.1.229 adds remote control resumption and fixes crashes

Claude Code version 2.1.229 introduces support for resuming recent Remote Control sessions via the `claude remote-control --continue` command and adds server-supplied hook support for self-hosted runners. This update also implements SSE keepalive pings to prevent idle-timeout disconnects on Vertex and Bedrock upstreams during long thinking pauses.

lab Claude Code Releases · 2d ago

Claude Code v2.1.228 fixes git detection, credential handling, and session bugs

Claude Code version 2.1.228 has been released with a series of bug fixes and improvements focused on stability and tool reliability. The update addresses issues with interactive sessions, Git detection on Windows, and Remote Control messaging.

media TLDR AI · 2d ago

Anthropic's Claude improves Riemann hypothesis bound; Meta releases Muse Glimmer; OpenAI launches GPT-5.6-Cyber

This edition of TLDR AI covers three major developments: Anthropic's Claude model significantly improved the lower bound for zeros satisfying the Riemann hypothesis, Meta released the open-weight Muse Glimmer model, and OpenAI introduced a specialized cybersecurity model.

media AI News (smol.ai) · 2d ago · 1 view

Meta releases Muse Glimmer 30B open-weight model; Anthropic improves Riemann bound

Meta released Muse Glimmer, a 30B dense multimodal model optimized for local agent deployment under Apache 2.0, while also promising future weights for Muse Spark 1.2.