All Recordings

Events overview

Browse on YouTube

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Alignment and Interpretability: How we Might Get It right

Been Kim

12/2023

Interpretability

Preparedness @ OpenAl

Aleksander Madry

12/2023

Governance

AGI Safety: Risks and Research Directions

Adam Gleave

12/2023

General

Understanding Planning in Neural Networks

Adrià Garriga-Alonso

12/2023

Interpretability

Lightning Talks (Day 2)

Multiple Speakers

02/2023

How Misalignment Could Lead to Takeover

Paul Christiano

02/2023

General

Lightning Talks (Day 1)

Multiple Speakers

02/2023

Aligning Massive Models: Current and Future Challenges

Jacob Steinhardt

02/2023

Supervising AI on Hard Tasks

Jan Leike

02/2023

Opening Remarks: Confronting the Possibility of AGI

Ilya Sutskever

02/2023

General

Surveying Safety Research Directions

Dan Hendrycks

02/2023

General

Looking Inside Neural Networks with Mechanistic Interpretability

Chris Olah

02/2023

Interpretability

“Situational Awareness” Makes Measuring Safety Tricky

Ajeya Cotra

02/2023

General

Research

Our research explores a portfolio
of high-potential agendas.

Events

Our events bring together
global leaders in AI.

Programs

Our programs build the field of trustworthy and secure AI