Upcoming

Stay tuned ...

Previous

• Learning Rewards from Natural Language by Ted Sumers, Wednesday Nov 8th 6-7pm @ Friend 008.

• New official Fall 2023 Princeton course COS597Q: AI Safety and Alignment, taught by Professor Elad Hazan.

• Talk by Richard Ngo of OpenAI, "AI Safety and the Alignment Problem". Saturday September 9th, 4pm @ Robertson 100.