A Claude Code Team Fireside Chat, Full Transcript and Video
Simon Willison published video and an annotated transcript of a fireside chat with Anthropic's Cat Wu and Thariq Shihipar covering Claude Code security, evals, and tool design.
What it is
A recorded conversation from the AI Engineer World's Fair between Simon Willison and two members of Anthropic's Claude Code team, published as both YouTube video and an edited transcript.
What it does
It covers Claude Code's design philosophy, coding agent security tradeoffs, how Anthropic builds and runs evals, tool design decisions, and how Anthropic's own engineers use these tools internally day to day, straight from the people building them.
Why it matters
Most Claude Code coverage is changelog parsing from the outside. This is a rare direct look at the reasoning behind decisions like sandboxing defaults and auto mode, useful context for anyone trying to predict where the tool is headed next.
How to use it
Watch the full session on YouTube or read Simon Willison's annotated transcript for the highlights and extra links.
Claude Fable 5 Goes Permanent for Max and Team Plans on July 20
Anthropic will make Claude Fable 5 a permanent part of Max and Team Premium plans starting July 20, 2026, at 50% of usage limits, with Pro and Team Standard users getting a one-time $100 credit.
docx, pptx, xlsx skills patched against path-traversal archives
Anthropic updated its docx, pptx, and xlsx Claude Agent Skills to reject symlink and path-traversal entries during archive extraction and to add template-format support.
Claude Code 2.1.214 closes a PowerShell permission bypass
Claude Code 2.1.214 fixes four permission-check bugs, including nested-directory allow rules matching too broadly and a bypass in Windows PowerShell 5.1 sessions.