Better Models: Worse Tools
A developer reports that newer Anthropic AI models, specifically Claude Opus 4.8 and Sonnet 5, are struggling with tool-calling schemas by inventing unnecessary fields. This regression in performance compared to older models highlights challenges in maintaining reliability as AI models become more complex.
Why it matters
As AI integration into software workflows increases, the reliability of tool-calling is critical for developers building automated systems.
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 with extra, invented fields in the nested edits[] array. And not Haiku or some small model: Opus 4.8. The edit itself is usually correct but the arguments do not match the schema as the model invents made-up keys and Pi thus rejects the tool call and asks to try again.
The article is a technical observation based on personal experience and testing, lacking political or social bias.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in