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

>The fact that LLMs don’t reflect a consistent inner model in that way

You're probably not going to ask any human a question about an image and get every single detail you want every time. If you care about a detail, just ask about it. Doesn't really have anything to do with a consistent inner model.



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

Search: