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

I’m not an expert and this is just a guess from the behavior but I feel like it’s kind of like giving the model a kind of Williams Syndrome, where (AFAIK) a common training process is that you keep asking it sensitive topics and every time it rejects the request you train it away from that and towards “Yeah, absolutely! Let’s go!!!” I feel like the natural result of this is that you’ll get something that is excited about whatever ideas you have?


Consider applying for YC's Fall 2026 batch! Applications are open till July 27.

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

Search: