So, a free idea from me: train the next coding LLM to produce not regular text, but patches which shortens code while still keeping the code working the same.

▲

NitpickLawyer 2 days ago | parent | next [-]

They can already do that. A few months ago I played around with the kaggle python golf competition. Got to top 50 without writing a line of code myself. Modern LLMs can take a piece of code and "golf" it. And modern harnesses (cc / codex / gemini cli) can take a task and run it in a loop if you can give them clear scores (i.e. code length) and test suites outside of their control (i.e. the solution is valid or not).

No idea why you'd want this in a normal job, but the capabilities are here.

	▲	actionfromafar 2 days ago \| parent [-]
		LLMs won't ever shut up. That seems unfixable. But a "hack" would perhaps be to train them to make longer patches but which actually removes code.

▲

wyre 2 days ago | parent | prev [-]

gonna tell claude to write all my code in one line

	▲	lomase 2 days ago \| parent [-]
		Imagine you are a Perl programmer writing js...