Today at 5:10pm PST: Talk by #ChatGPT lead engineer and @UCBerkeley alum John Schulman: Reinforcement Learning from Human Feedback: Progress and Challenges. Berkeley AI Research Lab @berkeley_ai @Berkeley_EECS Livestreamed:  https://
youtube.com/c/UCBerkeleyEE
CSEvents/live
…

→ View original post on X — @ken_goldberg,