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

I think there is a much simpler explanation behind this: training data.

Llms have had truck load of training on normal code than a super optimized ones.

That's why you will see it struggle with nginx configs. And on newer technology where there is less amount of data available.




If they trained an LLM on demoscene entries, maybe the results could be better, but I doubt by much.


I just upgraded by AI optimised graphics driver and now every time I launch COD every map is a psychedelic rave trance disco. Help!


I can help, but we gotta get through the 20 minutes of scrolling greets first.


A lot of demoscene optimizations are sacrificing correctness for speed, and thus not really applicable in most domains.


Refining and adding to the text and code they train on is a major area of focus at the moment. Things will definitely get better, but it will take time.


This is the key question... "What is the total information in this model and interaction?"




Consider applying for YC's Spring batch! Applications are open till Feb 11.

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

Search: