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

The main question is how did they do it? They must have some rules or facts 'book' (database, or something else), which is accessed by the model(s). It was a case earlier when ChatGPT falsely claimed someone was a criminal. And they fixed it quickly (within a few days, if I remember correctly), probably the same way.


Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: