Event details

Sep
9
The coming decades of AI development present one of the most pressing problems of our time. At the core of the concern is the alignment problem, potentially leading to dramatic ramifications for society.

Richard Ngo, AI governance researcher at OpenAI, previously research engineer at Deepmind, PhD of Machine Learning from Cambridge, will give us an introduction to the alignment problem: beyond getting AI systems to be capable of sophisticated, complex behaviors that have the potential for huge impact, how do we ensure that AI systems follow humans' intended goals, preferences, or ethical principles?

We will also give information about Princeton AI Alignment's programming for the semester, which includes introductory seminars for AI alignment and AI governance, as well as weekly paper reading groups and socials.

View physical accessibility information for campus buildings and find accessible routes using the Princeton Campus Map app.

Date

September 9, 2023

Time

2:30 p.m.

Location

Robertson Hall - 100 Arthur Lewis Auditorium

Audience