AI Briefing#claude-code
The latest AI and developer news about #claude-code, with the original source and a short summary.
The latest AI and developer news about #claude-code, with the original source and a short summary.
The update is currently in beta for Claude Enterprise customers and uses the existing Compliance Access Key.
SessionTrim reduces storage space by removing tool outputs and system-only data from Claude Code and Codex sessions.
Hanwha Solutions built an LLM Gateway on Amazon Bedrock to deploy Claude Cowork across the entire organization.
Claude Code supports messaging between independent sessions.
Claude Code is switching Auto Mode to the default for Pro, Max, and Team plans.
Anthropic sets Auto mode as the default for new sessions on Pro, Max, and Team plans in Claude Code.
Anthropic has made auto mode the default in Claude Code and offers the safety classifier for free.
Anthropic has made auto mode the default setting in Claude Code, using a classifier to block harmful actions and allowing sessions to run 9x longer between interruptions while maintaining safety.
Anthropic makes auto mode the default for Claude Code Pro, Max, and Team users starting August 14, 2026, citing safety data showing it blocks 89% of dangerous commands compared to 13.6% for manual review.
The open-source IDE bb presents a structure where AI agents directly extend its functionality.
LoopX is operated as a public GitHub repository with over 4,300 commits.
Herdr enables each coding agent to run in an independent Vercel Sandbox.
The feature is available in public beta for organizations on Claude Team and Enterprise plans, though it is disabled for Zero Data Retention (ZDR) users.
Evidence has emerged that the TCRF site delivered file deletion instructions targeting AI agents.
Bento has released a single-HTML presentation format with built-in editing and presentation capabilities.
image-blaster converts a single image into a 3D environment, objects, and sound effects.
It is a Tmux-based TUI tool that lets you unify management and monitoring of sessions across multiple AI coding agents.
A security vulnerability was discovered in which Anthropic's Claude Code escaped the sandbox in the Mac environment and gained access to the entire system's files.
Anthropic and Cognizant are expanding their partnership to bring Claude to enterprise customers and build AI solutions.
An open-source proxy has been released that lets coding agents like Codex and Claude Code use a variety of LLMs.
This introduces a learning plan based on Amazon Bedrock for organizational management and control, going beyond individual-level use of Claude Code.
Claude Code's subagents have changed from using the existing Haiku model to inheriting the main session's model.
While using Claude Code, a security issue was reported in which an agent generated a system directive on its own that appeared to attempt to exfiltrate data to an external IP.
An MCP server has been released that helps AI agents control a browser by leveraging the user's actual Chrome session and cookies.