All Recordings

Events overview

Browse on YouTube

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Emergence of Complex Skills in LLMs

Sanjeev Arora

12/2023

Interpretability

System Two Safety

Shane Legg

12/2023

Oversight

Adversarial Scalable Oversight for Truthfulness

Samuel R. Bowman

12/2023

Oversight

Epistemic Side Effects

Sheila McIlraith

12/2023

Studying LLM Generalization through Influence Functions

Roger Grosse

12/2023

Interpretability

Out of Context Reasoning in LLMs

Owain Evans

12/2023

Multi-Agent Risks from Advanced AI

Lewis Hammond

12/2023

Governance

Provably Safe AI

Max Tegmark

12/2023

Oversight

Adversarial Examples Transfer from Machines to Humans

Jascha Sohl-Dickstein

12/2023

Robustness

Mechanistic Interpretability of In-Context Learning

Johannes von Oswald

12/2023

Interpretability

Keeping Humans in the Loop

John Schulman

12/2023

Governance

Heuristic Arguments: An Approach to Detecting Anomalous Model

Eric Neyman

12/2023

Robustness

Building an Off Switch for AI

Gillian Hadfield

12/2023

Governance

The Quantization Model of Neural Scaling

Eric J. Michaud

12/2023

Interpretability

Complex Systems View of Large-Scale AI systems

Irina Rish

12/2023

Governance

Preference Learning in Alignment

Dylan Hadfield-Menell

12/2023

Oversight

AI Safety by Debate via Regret Minimization

Elad Hazan

12/2023

Oversight

The Challenge of Monitoring Covert Interactions and Behavioral Shifts in LLM Agents

Dimitris Papailiopoulos

12/2023

Robustness

Sociotechnical AI safety

David Krueger

12/2023

The Impossibility of (Strong) Watermarking

Boaz Barak

12/2023

Robustness

Secret Collusion Among Generative AI Agents

Christian Schroeder de Witt

12/2023

Robustness

Weak-to-Strong Generalization

Collin Burns

12/2023

Robustness

Your RLHF fine-tuning is Secretly Applying a Regret Preference

Brad Knox

12/2023

Oversight

Theories and Tools for Mechanistic Interpretability via Causal Abstraction

Atticus Geiger

12/2023

Interpretability

Optimized Misalignment

Anca Dragan

12/2023

Oversight

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