The Anthropic models have always been annoying this way -- chatty/opinionated and Dunning-Krugerish. And love to run away and do things unprompted with me jamming my ESC ESC ESC key over and over so I can get a word in edgewise.

FWIW Codex/GPT models are way less this way. Maybe to a fault.

I'm setting up my DGX Spark to try Qwen 3.6 27B again, as I'm hearing a lot of good reviews. When I tried it some time ago it was still early for support in llama.cpp.