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

We have tried many of the current open source models but unfortunately the only model whose capability is close to GPT-4 is Deepseek and unfortunately Deepseek can’t follow our specified format and is very sensitive to prompt changes.


The other problem is with latency: Deepseek 34B on A100s seem slower than GPT-4 but perhaps it will be better on H100s.




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

Search: