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

We've done a bunch of work to strip down the context and minimise the output tokens (which tends to be 100x as slow as input tokens). GPT-4o is pretty fast too :)


Thanks for the explanation. Can't wait to see the code when you open it up!




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

Search: