Virtual Q&A w/ Joe Benton (METR / Anthropic)

Join us for a live Q&A with Joe Benton. Hear how he got into AI safety, what safety research at a frontier AI lab looks like, and how students can get involved. The event is co-hosted with Columbia's AI Alignment Club.

Joe Benton previously led the scalable oversight research team at Anthropic. He is now joining METR to increase transparency around the risks from AI systems. Joe was also the research lead for the Anthropic Fellows program and helped set up the UK Frontier AI Taskforce (now the UK AI Security Institute)

Location:Silver Center room 120. Virtual attendance will not be supported.

Logistics:- Open to all members of the NYU community- Pizza and drinks provided!- 7:45-8:00 PM Check in, get food, mingle- 8:00-8:45 PM Moderated Q&A- 8:45-9:00 PM Free Q&A