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

yeh, but the main problem is the quality. with algorithm bug can be fixed. with llm it's more complicated. in practice they do some mistakes consistently, and in some cases cannot recover even with assistance. (don't take me wrong, I'm very happy with the results most of the time)



You just fix the mistakes and keep moving. It's like autocomplete where you still need to fill in the blanks or select a different completion.


Spotting and fixing mistakes in a LSC is no small feat.




Consider applying for YC's Summer 2025 batch! Applications are open till May 13

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

Search: