> This doesn't make sense as long as LLMs are non-deterministic. I think we will... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Ozzie_osman 3 months ago \| parent \| context \| favorite \| on: Getting AI to work in complex codebases > This doesn't make sense as long as LLMs are non-deterministic. I think we will find ways around this. Because humans are also non-deterministic. So what do we do? We review our code, test it, etc. LLMs could do a lot more of that. Eg, they could maintain and run extensive testing, among other ways to validate that behavior matches the spec.

maltalex 3 months ago [–]

If you're reviewing the code, then you're no longer "opening python files with the same frequency that you open up a hex editor to read assembly".

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact