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

This quote is by Dr. Paul Christiano, PhD Inventor of OpenAI's Deep Reinforcement Learning from Human Preferences (RHLF).

Start of thread: https://twitter.com/liron/status/1650980681953198080

Full video, "How to Solve AI Alignment with Paul Christiano": https://www.youtube.com/watch?v=GyFkWb903aU



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

Search: