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

OP. We migrated to GPT-5 when it came out but found that it performs worse than 4.1 when you pass lots of context (up to 100K tokens in some cases). We found that it:

a) has worse instruction following; doesn't follow the system prompt b) produces very long answers which resulted in a bad ux c) has 125K context window so extreme cases resulted in an error

Again, these were only observed in RAG when you pass lots of chunks, GPT-5 is probably a better model for other taks.



love the share, ty




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

Search: