Live data from Hacker News

Ask HN: Can LLM's produce useful code?

news.ycombinator.com

11–12 of 12 posts

Re: Ask HN: Can LLM's produce useful code?

#11

I evaluated the Jetbrains assistant. I was more impressed with its ability to chat about science fiction than actual programming. It could do some impressive things. I was working on a codebase that used JooQ to generate SQL code. The agent did not have access to the database or SQL scripts but it could figure out what the SQL schema was by looking at the Jooq stubs. I tried to use it to write a somewhat complex quer…

> Other tasks have an element of looping which is really fundamental in computer science Have you tried any of these agent based workflows that claim to be able to loop with some amount of reasoning ?

No, but I have read many papers where people have some success but don't really get it to work consistently.

From Godel, Escher, Bach and my own experience I'm afraid that's a way to spend the next 1000 years pushing a bubble around under a rug.

If you had something that fully automated the cycle of running the compiler and running tests at least I wouldn't have the tedium of doing all that, particularly the bit about having to reprompt with the last compiler error.

Re: Ask HN: Can LLM's produce useful code?

#12

Earlier quoted context omitted.

> Other tasks have an element of looping which is really fundamental in computer science Have you tried any of these agent based workflows that claim to be able to loop with some amount of reasoning ?

No, but I have read many papers where people have some success but don't really get it to work consistently. From Godel, Escher, Bach and my own experience I'm afraid that's a way to spend the next 1000 years pushing a bubble around under a rug. If you had something that fully automated the cycle of running the compiler and running tests at least I wouldn't have the tedium of doing all that, particularly the bit abou…

Right. I think the ability to run tests/compilation as a feedback mechanism is definitely interesting .

I wonder whether the problem is that its landed on an incorrect output sample (i.e re-sampling another code output would fix it ) .. vs … a feedback loop on the compiler output is what it really needs ..

Post reply on HN