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

Those are 2024-era criticisms of LLMs for code.

Late 2025 models very rarely hallucinate nonexistent core library functionality - and they run inside coding agent harnesses so if they DO they notice that the code doesn't work and fix it.





get ready to tick those numbers over to 2026!



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

Search: