> When it’s able to create code that compiles, the code is invariably inefficient and ugly.

Why not have static analysis tools on the other side of those generations that constrain how the LLM can write the code?

▲

jdiff 2 hours ago | parent [-]

I'd be interested to know the answer to this as well. Considering the wealth of AI IDE integrations, it's very eyebrow-raising that there are zero instances of this. Seems like somewhat low hanging fruit to rule out tokens that are clearly syntactically or semantically invalid.

	▲	hkt an hour ago \| parent [-]
		This can be done: I gave mine a justfile and early in the project very attentively steered it towards building out quality checks. CLAUDE.md also contains instructions to run those after each iteration. What I'd like to see is the CLI's interaction with VSCode etc extending to understand things which the IDE has given us for free for years.