Skip to main content

All Recordings

Topic
Event series

Year

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Results 1

Showing items 1 to3 of 6

Sort by
Filtering by:
Tag
Operator
Value

Why Language Models Hallucinate

Santosh Vempala

•

December 1, 2025

Alignment Foundations

Alignment Workshop

2025

What Does It Mean for Agentic AI to Preserve Privacy?

Niloofar Mireshghallah

•

December 1, 2025

AI Security & Verification

Alignment Workshop

2025

Toy Models for Task-Horizon Scaling

Cozmin Ududec

•

December 1, 2025

Science of Deep Learning

Alignment Workshop

2025

The State and the Science of AI-Bio Evals

Bryce Cai

•

December 1, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

State of Jailbreaks

Xander Davies

•

December 1, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Privacy and Security Challenges in AI Agents

Kamalika Chaudhuri

•

December 1, 2025

AI Security & Verification

Alignment Workshop

2025

Peril and Potentials of Training with Lie Detectors

Chris Cundy

•

December 1, 2025

Deception

Alignment Workshop

2025

Our Pivot To Pragmatic Interpretability

Neel Nanda

•

December 1, 2025

Interpretability

Alignment Workshop

2025

Measuring AI Systems’ Ability to Influence Humans

Anna Gausen

•

December 1, 2025

AI, Society & Values

Alignment Workshop

2025

How do we know what AI can (and can't) do?

Anka Reuel

•

December 1, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Hidden Pitfalls of AI Scientist Agents

Atoosa Kasirzadeh

•

December 1, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Guarding the Age of Agents

Bo Li

•

December 1, 2025

AI Security & Verification

Alignment Workshop

2025

Current State of AI Agent Security

Andy Zou

•

December 1, 2025

Misuse & Safeguards

Alignment Workshop

2025

AI + Democracy

Divya Siddarth

•

December 1, 2025

Governance & Policy

Alignment Workshop

2025

Toward Scalable and Actionable Interpretability

Yonatan Belinkov

•

November 30, 2025

Interpretability

Alignment Workshop

2025

Scalable Oversight and Understanding

Sarah Schwettmann

•

November 30, 2025

AI Control & Oversight

Alignment Workshop

2025

San Diego Alignment Workshop 2025 Opening Remarks

Adam Gleave

•

November 30, 2025

Alignment Foundations

Alignment Workshop

2025

Provably Safe AI

Max Tegmark

•

November 30, 2025

Governance & Policy

Alignment Workshop

2025

Powerful Open-Weight AI Models: Wonderful, Terrible & Inevitable

Stephen Casper

•

November 30, 2025

Misuse & Safeguards

Alignment Workshop

2025

Polarity-Aware Probing for Quantifying Latent Alignment in LMs

Chirag Agarwal

•

November 30, 2025

Interpretability

Alignment Workshop

2025

Multi-agent RL for Provably Robust LLM Safety

Natasha Jaques

•

November 30, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Lessons Learned from the First Misalignment Safety Case

Samuel Bowman

•

November 30, 2025

Alignment Foundations

Alignment Workshop

2025

Frontier AI in Cybersecurity: Risks, Challenges & Future Directions

Dawn Song

•

November 30, 2025

AI Security & Verification

Alignment Workshop

2025

Finding & Reactivating Safety Mechanisms of Post-Trained LLMs

Yisen Wang

•

November 30, 2025

Misuse & Safeguards

Alignment Workshop

2025

Eval Awareness is Becoming a Problem

Marius Hobbhahn

•

November 30, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Disentangling Agency & Predictive Power Without Solving ELK

Yoshua Bengio

•

November 30, 2025

Alignment Foundations

Alignment Workshop

2025

Consensus Sampling for Safer Generative AI

Adam Kalai

•

November 30, 2025

Misuse & Safeguards

Alignment Workshop

2025

Chain of Thought Monitorability for AI Safety

Tomek Korbak

•

November 30, 2025

AI Control & Oversight

Alignment Workshop

2025

Automating Mechanistic Interpretability

Chenhao Tan

•

November 30, 2025

Interpretability

Alignment Workshop

2025

AI Control Needs Redteaming

Asa Cooper-Stickland

•

November 30, 2025

AI Control & Oversight

Alignment Workshop

2025

AI Agent Benchmarks Are Broken

Daniel Kang

•

November 30, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

A Practical Approach to Verifying Code at Scale

Maja Trębacz

•

November 30, 2025

AI Control & Oversight

Alignment Workshop

2025

Low probability estimation

Jacob Hilton

•

October 28, 2025

Science of Deep Learning

FAR Seminar

2025

Can you just train models not to scheme?

Marius Hobbhahn

•

October 7, 2025

Deception

FAR Seminar

2025

Singular Learning Theory and AI Safety

Jesse Hoogland

•

September 16, 2025

Science of Deep Learning

FAR Seminar

2025

What Would it Take to Stop the Development of Superintelligence? A Treaty Proposal

Aaron Scher

•

August 26, 2025

Superintelligence & Frontier Risk

FAR Seminar

2025

The EU Code of Practice: Towards a Global Standard for Frontier AI Risk Management

Siméon Campos

•

August 19, 2025

Governance & Policy

FAR Seminar

2025

Alignment is social: lessons from human alignment for AI

Gillian Hadfield

•

August 5, 2025

AI, Society & Values

FAR Seminar

2025

Realigning AI

Zhijing Jin

•

June 17, 2025

Alignment Foundations

FAR Seminar

2025

Verifiable Compute & Building Trust in Agentic Supply Chains

Tina Morrison

•

May 31, 2025

Governance & Policy

TIAP

2025

Sandpaper Socks: Operational Considerations in AI Evals

Olivia Shoemaker

•

May 31, 2025

Evaluations & Red-Teaming

TIAP

2025

Rising Cost of Evaluations, Falling Cost of Intelligence

Ben Cottier

•

May 31, 2025

Evaluations & Red-Teaming

TIAP

2025

Regulation of Frontier Models, Confidential Computing & AI Alignment

Bill Foster

•

May 31, 2025

Governance & Policy

TIAP

2025

Prioritizing Technical Governance Investments: Verification

Robert Trager

•

May 31, 2025

Governance & Policy

TIAP

2025

Policy-Oriented AI Evaluations

Kevin Wei

•

May 31, 2025

Evaluations & Red-Teaming

TIAP

2025

Normal Policy Tools for a Normal Technology

Asad Ramzanali

•

May 31, 2025

Governance & Policy

TIAP

2025

National Security & Defense

Steve Kelly

•

May 31, 2025

Governance & Policy

TIAP

2025

Hydropower: the Missing Piece

Charles Yang

•

May 31, 2025

Governance & Policy

TIAP

2025

Hardware-Enabled Verifiability as a Data Center Security Property

Onni Aarne

•

May 31, 2025

Governance & Policy

TIAP

2025

DoD & AGI Preparedness

Mark Beall

•

May 31, 2025

Governance & Policy

TIAP

2025

Day 2 Opening Remarks

Lennart Heim

•

May 31, 2025

Governance & Policy

TIAP

2025

Compute in America: Playbook for Secure Clusters at Home

Arnab Datta

•

May 31, 2025

Governance & Policy

TIAP

2025

CVE-Bench

Daniel Kang

•

May 31, 2025

Evaluations & Red-Teaming

TIAP

2025

Application of Cryptographic Primitives in AI Accelerators

Fatemeh Ganji

•

May 31, 2025

Governance & Policy

TIAP

2025

Access Considerations for Generative AI Systems Beyond Release

Irene Solaiman

•

May 31, 2025

Governance & Policy

TIAP

2025

AI-Military Integration Under President Trump

Hamza Chaudhry

•

May 31, 2025

Governance & Policy

TIAP

2025

AI Supply Chains: An Emerging Ecosystem of AI Dependencies

Sarah Cen

•

May 31, 2025

Governance & Policy

TIAP

2025

AI National Security Policy: Industry and Government

Sara McNaughton

•

May 31, 2025

Governance & Policy

TIAP

2025

14 Ways of Looking at AI

Brad Carson

•

May 31, 2025

Governance & Policy

TIAP

2025

Unresolved Debates on the Future of AI

Helen Toner

•

May 30, 2025

Governance & Policy

TIAP

2025

Making Sense of the AI Auditing Ecosystem

Miranda Bogen

•

May 30, 2025

Governance & Policy

TIAP

2025

Frontier Model Safety

Rep. Alex Bores

•

May 30, 2025

Governance & Policy

TIAP

2025

Day 1 Opening Remarks

Adam Gleave

•

May 30, 2025

Governance & Policy

TIAP

2025

An Overview of Technical AI Governance

Ben Bucknall

•

May 30, 2025

Governance & Policy

TIAP

2025

AI Control: Addressing Risks from Agentic Internal Deployments

Mary Phuong

•

May 30, 2025

AI Control & Oversight

TIAP

2025

Scaling Alignment Research via Safety Cases

Jacob Pfau

•

April 23, 2025

Alignment Foundations

Alignment Workshop

2025

Emergent Misalignment

Owain Evans

•

April 23, 2025

Deception

Alignment Workshop

2025

Jailbreaking Aligned LLMs, Reasoning Models & Agents

Siva Reddy

•

April 23, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Antidistillation Sampling

Zico Kolter

•

April 23, 2025

AI Security & Verification

Alignment Workshop

2025

Unthinking Vulnerability of Large Reasoning Models

Baoyuan Wu

•

April 23, 2025

Misuse & Safeguards

Alignment Workshop

2025

Computational Safety for Generative AI

Pin-Yu Chen

•

April 23, 2025

Misuse & Safeguards

Alignment Workshop

2025

LLM Safety Training & Semantically Related Natural Prompts

Sravanti Addepalli

•

April 23, 2025

Misuse & Safeguards

Alignment Workshop

2025

Your DPO Algorithm is Secretly a Misspecified Reward Estimator

Aditya Gopalan

•

April 23, 2025

Alignment Foundations

Alignment Workshop

2025

CVE-Bench: A Real-World Cybersecurity Benchmark for AI Agents

Daniel Kang

•

April 23, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Next Steps for Control Safety Cases

Martín Soto

•

April 23, 2025

AI Control & Oversight

Alignment Workshop

2025

High-Compute Alignment & Control

Noam Brown

•

April 23, 2025

AI Control & Oversight

Alignment Workshop

2025

A New Definition & Improved Mitigation for Reward Hacking

Cassidy Laidlaw

•

April 23, 2025

Alignment Foundations

Alignment Workshop

2025

Value Compass Leaderboard: Platform for LLMs’ Value Evaluation

Xiaoyuan Yi

•

April 22, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

STAIR: Improving Safety Alignment with Introspective Reasoning

Yinpeng Dong

•

April 22, 2025

Misuse & Safeguards

Alignment Workshop

2025

Unified Explanation of DNN Inference Logic & Representation

Huiqi Deng

•

April 22, 2025

Interpretability

Alignment Workshop

2025

Persuade AIs

Weiyan Shi

•

April 22, 2025

Misuse & Safeguards

Alignment Workshop

2025

Evaluating Alignment Processes Rather than Models

Adam Kalai

•

April 22, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Disaster Preparedness for AI Safety

Tegan Maharaj

•

April 22, 2025

AI, Society & Values

Alignment Workshop

2025

You Should Work on Agent Infrastructure

Alan Chan

•

April 22, 2025

AI Security & Verification

Alignment Workshop

2025

Governing AI Agents Under the EU AI Act

Robin Staes-Polet

•

April 22, 2025

Governance & Policy

Alignment Workshop

2025

The White House AI Action Plan

Mark Brakel

•

April 22, 2025

Governance & Policy

Alignment Workshop

2025

In-House Evaluation is Not Enough

Shayne Longpre

•

April 22, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Deceptive Alignment & Thinking Monitor in LLMs

Jiaming Ji

•

April 22, 2025

Deception

Alignment Workshop

2025

Safety Benchmarking & Testing of Multimodal LLMs

Tianwei Zhang

•

April 22, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Alignment on the Fly

Furong Huang

•

April 22, 2025

Alignment Foundations

Alignment Workshop

2025

Safety Alignment of LLMs

Animesh Mukherjee

•

April 22, 2025

Misuse & Safeguards

Alignment Workshop

2025

Exploring Cooperation & Alignment

Kalesha Bullard

•

April 22, 2025

AI, Society & Values

Alignment Workshop

2025

AI Catastrophic Risks & Scientist AI Solution

Yoshua Bengio

•

April 22, 2025

Superintelligence & Frontier Risk

Alignment Workshop

2025

Powering up AI Capability Evaluations with Model Tampering Attacks

Stephen Casper

•

April 22, 2025

Evaluations & Red-Teaming

Alignment Workshop

2025

Control, Cooperation and AI Welfare

Kathleen Finlinson

•

March 28, 2025

AI Control & Oversight

ControlConf

2025

Subversion Strategy Evaluation

Charlie Griffin

•

March 28, 2025

AI Control & Oversight

ControlConf

2025

[Fireside Chat] Control & Computer Security

Steve Kelly

•

March 28, 2025

AI Control & Oversight

ControlConf

2025

AI Control Safety Cases

Tomek Korbak

•

March 28, 2025

AI Control & Oversight

ControlConf

2025

Frontier Models are Capable of In-context Scheming

Alexander Meinke

•

March 27, 2025

Deception

ControlConf

2025

Task Decomposition for AI Control

Aaron Sandoval

•

March 27, 2025

AI Control & Oversight

ControlConf

2025

There are no available cars matching the current filters.