pi

1 article

← All topics

Better Models, Worse Tools: Claude tool calls regress on Sonnet 5 and Opus 4.8
anthropicclaude-opus-4-8claude-sonnet-5tool-useclaude-code+4

Armin Ronacher's controlled tests show Claude Opus 4.8 and Sonnet 5 produce ~20% malformed tool calls against Pi's edit tool; older models are clean.