All Recordings

Events overview

Browse on YouTube

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

AI Policy in China

Kwan Yee Ng

10/2024

Governance

AI Control

Buck Shlegeris

10/2024

METR Updates & Research Directions

Beth Barnes

10/2024

Model Evaluation

Implications of Human Model Misspecification for Alignment

Anca Dragan

10/2024

General

Formal Verification is Overrated

Zac Hatfield-Dodds

10/2024

Formal Methods

Using Formal Languages

Sheila McIlraith

10/2024

Formal Methods

Tamper-Resistant Safeguards for Open-Weight LLMs

Mantas Mazeika

10/2024

MobileSafetyBench

Kimin Lee

10/2024

Backdoors as an Analogy for Deceptive Alignment

Jacob Hilton

10/2024

Alignment Stress-Testing at Anthropic

Evan Hubinger

10/2024

The (Un)Reliability of Chain-of-Thought Reasoning

Chirag Agarwal

10/2024

Value Pluralism and AI Value Alignment

Atoosa Kasirzadeh

10/2024

Value Alignment

Gradient Routing

Alex Turner

10/2024

3 Mechanisms Underlying Emergent Abilities in Generative Models

Hidenori Tanaka

10/2024

Campaigns in Emerging Issues: Lessons Learned from the Field

Andrew Freedman

08/2024

Governance

Deceptive Instrumental Alignment

Evan Hubinger

07/2024

Verification & Confidence Building for International Coordination

Peter Barnett

07/2024

Formal Methods

Current Issues in AI Safety

Multiple Speakers

07/2024

General

Research Proposal: The Three-Layer Paradigm

Zhaowei Zhang

07/2024

Game Theory and Social Choice for Cooperative AI

Vincent Conitzer

07/2024

Powering Up Capability Evaluations

Stephen Casper

07/2024

Model Evaluation

AI: What If We Succeed?

Stuart Russell

07/2024

General

Scalable Oversight: A Rater Assist Approach

Sophie Bridgers

07/2024

Oversight

Challenges With Unsupervised LLM Knowledge Discovery

Vikrant Varma

07/2024

What are Human Values, and How Do We Align AI to Them?

Oliver Klingefjord

07/2024

Value Alignment

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