Better Models: Worse Tools | Armin Ronacher's Thoughts and Writings
lucumr.pocoo.org · 2,300 words · saved by 1 readers
About an aggravating tool-calling regression in newer Claude models.
written on July 04, 2026 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. That alone is not too surprising as models emit malformed tool calls sometimes. Particularly small ones. What surprised me is that this is getting…
saved by
related reading
- An update on recent Claude Code quality reports \ Anthropicanthropic.com
- Did Claude 3 Opus align itself via gradient hacking? — LessWronglesswrong.com
- Coding Models Are Doing Too Much | whnrehiew.github.io
- Alignment is not solved but it increasingly looks solvablealigned.substack.com
- Teaching Claude Whyalignment.anthropic.com
- Prompting best practicesdocs.anthropic.com
- Don’t Outsource Your Thinkingteltam.github.io
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Teaching Claude why \ Anthropicanthropic.com
- How I Use Claude Code | Philipp Spiessspiess.dev
- Simulated Users & Sad LLMs1a3orn.com