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

Sorry to say but the solution is to stop using python. The models are trained to code defensively assuming historically representative python codebases. The models trust the types a lot more in languages where the canonical historical examples trust the types because the language is constructed around that premise.


I would expect a language model to do a better job of coping with that kind of uncertainty, inferring type from name and usage, etc.




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

Search: