Armin Ronacher's Thoughts and Writings · Armin Ronacher ·

Claude Opus 4.8 and Sonnet 5 seem worse at tool calls than older models, likely due to post-training that assumes Claude Code-like harnesses as targets

A very strange Pi issue sent me down a rabbit hole over the last two days. The short version is that newer Claude models sometimes call Pi's edit tool …

Lead Source

More

RuntimeWire: RuntimeWire
Simon Willison's Weblog: Simon Willison's Weblog
OpenAI: OpenAI

Discussion