Stop Making Models Smarter

I like to use 'dumber' models (like Composer 1.5, which is possibly a fine-tuned Qwen) even though it requires much more specific outlined guidance from me.

Claude Opus 4.6, which is probably the 'smartest' model out there, is great at "one-shotting" - but I find I rarely want to one-shot anything, unless its a really small discrete element, which a dumb model can one-shot as well.

There are funny examples of telling Claude "Make a game about Dadaist frogs that uses a betting mechanic where you try to become the richest frog in the pond. Make no mistakes." And Claude executes something that runs, and more or less is what you asked for.

For real work, I like that the dumb models don't know as much. I noticed they use web search more agressively because of their lack of knowledge, for example. (Although tool use can be improved via system prompts.) I also feel that dumber models have less bad opinions. Claude tends to jump to conclusions - it almost needs more guardrails because it's smarter (and a little overconfident?)

Curious what others' experience is.