Comment on Are LLMs capable of writing *good* code?

recapitated@lemmy.world ⁨3⁩ ⁨months⁩ ago

I’m my experience they do a decent job of whipping out mindless minutea and things that are well known patterns in very popular languages.

They do not solve problems.

I think for an “AI” product to be truly useful at writing code it would need to incorporate the LLM as a mere component, with something facilitating checks through static analysis and maybe some other technologies, maybe even mulling the result through a loop over the components until they’re all satisfied before finally delivering it to the user as a proposal.

source
Sort:hotnewtop