mikaelaast

That’s very intriguing. I guess it would involve specifying a mental model in clear enough terms for it to be comparable to an already verified model, or something.

I like this. The few-shot example snippet method is something I’d like to incorporate in my workflow, to better align generated code with my preferences.

(Those are hardly analogous comparisons to LLM generated code, are they?)

So you do a vibe check?

If it’s in the second category, I struggle not to mentally model it. How do you stop yourself? And should you?

How do you verify the code without actually looking at it?

Creating work for the clean-up crew and leaving good money on the table for them (because it ain't gonna be cheap).

Yes, and I like the points you are making. I feel like the mental models we make are exercises in a purer form of knowledge building than the code artifacts we produce. A kind of understanding that is liberated from the confines of languages.