schema-overfitting

Tag

Cards List
#schema-overfitting

@yibie: Recommended article: Flask author Armin Ronacher, while tracking a Pi bug, discovered a troubling fact: the tool calling of the new Claude models (Opus 4.8, Sonnet 5) is regressing—not improving but worsening. And he found the root cause: RL...

X AI KOLs Timeline · 2d ago Cached

Flask author Armin Ronacher found that the tool-calling ability of the new Claude models (Opus 4.8, Sonnet 5) is degrading. The root cause is that RL post-training over-adapts to Claude Code's own tool schema, making alternative tool schemas increasingly difficult to generate correctly. The article reveals the phenomenon of models performing worse rather than better on specific tool-calling scenarios, offering an important caution for agent development.

0 favorites 0 likes
← Back to home

Submit Feedback