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

Were you using o3-mini before o3 came out? I wonder if o3-mini has had the same issues if it is from the same series of models.


I think I saw o3 hallucinate more in a single day of heavy use then I saw o3-mini do in a month.

That said: so far, I'm putting up with it because o3 is smart.


What does that mean? Smart?


It means some of those hallucinations works. So if you build a test harness hallucinations can let you solve problems you couldn't solve without them.

That test harness can be a human checking the results, it is more work for the human but it will solve more problems than without the hallucinations.




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

Search: