Hacker News new | past | comments | ask | show | jobs | submit login

As an author of this paper, I am very excited see the great discussion here!

Several people mentioned the generation - compilation - fixing loop. Just want to remind you that our approach works for not only the generation step but also the fixing step. This is because fixing is essentially asking LLMs to generate a new version of the code. The paper actually has a "repair" experiment to demonstrate this and our approach achieves significant gain in this experiment, i.e., 37% relative improvement in functional correctness.




37% gain relative to what? What percent of generated functions were incorrect?


compared to vanilla LLM decoding.


Thank you for your research really impressive work!




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: