All Recordings

Events overview

Browse on YouTube

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

AI Control and Why AI Security People Should Care

Buck Shlegeris

02/2025

Security

Governance Challenges of Biological AI Models

Melissa Hopkins

02/2025

Governance

Set Laws AI Must Prove It's Following

Evan Miyazono

02/2025

Governance

How Policy Changes are Effectively Implemented within the US Government

Austin Carson

02/2025

Governance

AI's Implications for Nuclear Weapons Systems

Philip Reiner

02/2025

Security

Impact of Frontier AI in the Landscape of Cyber Security

Dawn Song

02/2025

Security

Safeguards in 2025+

Xander Davies

02/2025

Security

flexHEG

David A. Dalrymple (davidad)

02/2025

Security

The AI Security Landscape

Sella Nevo

02/2025

Security

EU CoP's Security Focus

Yoshua Bengio

02/2025

Security

Plan B: Training LLMs to fail less severely

Julian Stastny

02/2025

Eliciting the capabilities of scheming LLMs

Fabien Roger

01/2025

Empirical Progress on Debate

Julian Michael

10/2024

Oversight

Targeted Manipulation & Deception

Micah Carroll

10/2024

Oversight

Will Scaling Solve Robustness?

Adam Gleave

10/2024

Robustness

Paradigms and Robustness

Alex Wei

10/2024

Robustness

Generalized Adversarial Training and Testing

Stephen Casper

10/2024

Robustness

Improving AI Safety with Top-Down Interpretability

Andy Zou

10/2024

Interpretability

State of Interpretability & Ideas for Scaling Up

Atticus Geiger

10/2024

Interpretability

Third-Party Evals: Learnings from Harmony Intelligence

Soroush Pour

10/2024

Model Evaluation

Reframing AGI Threat Models

Richard Ngo

10/2024

A Safe Harbor for AI Evaluation & Red Teaming

Shayne Longpre

10/2024

AGI-Complete Evaluation

Joel Z. Leibo

10/2024

Model Evaluation

Connecting Capability Evals to Danger Thresholds

David Duvenaud

10/2024

Model Evaluation

A Sociotechnical Approach to a Safe, Responsible AI Future

Dawn Song

10/2024

Governance

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