![Adam Kalai - Consensus Sampling for Safer Generative AI [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2F0dp7iZtbpYM%2Fmqdefault.jpg)
5:42
5:42
![Daniel Kang - AI Agent Benchmarks Are Broken [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2F4iyMb0ARiao%2Fmqdefault.jpg)
5:11
![Cozmin Ududec - Toy Models for Task-Horizon Scaling [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FdikjGE5hRhg%2Fmqdefault.jpg)
5:23
![Chirag Agarwal - Polarity-Aware Probing for Quantifying Latent Alignment in LMs [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FzgPRw4qGVMM%2Fmqdefault.jpg)
5:08
![Niloofar Mireshghallah - What Does It Mean for Agentic AI to Preserve Privacy? [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FnPFM27SI6VY%2Fmqdefault.jpg)
5:15
![Yoshua Bengio - Disentangling Agency & Predictive Power Without Solving ELK [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FZndiBDmss-w%2Fmqdefault.jpg)
30:57
55:00
![Anna Gausen - Measuring AI Systems’ Ability to Influence Humans [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2F2xF3knXanHU%2Fmqdefault.jpg)
9:30
![Santosh Vempala - Why Language Models Hallucinate [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FbtToTJw0KFE%2Fmqdefault.jpg)
5:08
![Natasha Jaques - Multi-agent RL for Provably Robust LLM Safety [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FKe4t7qsBJLg%2Fmqdefault.jpg)
5:19
![Marius Hobbhahn - Eval Awareness is Becoming a Problem [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FGUS_88tPcf4%2Fmqdefault.jpg)
10:21
![Chris Cundy - Peril and Potentials of Training with Lie Detectors [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FOpqeB-eZx68%2Fmqdefault.jpg)
5:05
![Divya Siddarth - AI + Democracy [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FqLJq3J50X7E%2Fmqdefault.jpg)
10:24
![Sarah Schwettmann - Scalable Oversight and Understanding [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2F8oJW7hdbc2I%2Fmqdefault.jpg)
5:42
![Xander Davies - State of Jailbreaks [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FEoLb5OgyrXQ%2Fmqdefault.jpg)
6:56
![Max Tegmark - Provably Safe AI [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FzBX7FCH3JAE%2Fmqdefault.jpg)
5:14
10:25
55:19
![Asa Cooper Stickland - AI Control Needs Redteaming [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FUjG7aD_atus%2Fmqdefault.jpg)
9:21
![Adam Gleave – STACK: Adversarial Attacks on LLM Safeguard Pipelines [AAAI 2026]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FMPp68Czk4qE%2Fmqdefault.jpg)
9:25
![Tomek Korbak - Chain of Thought Monitorability for AI Safety [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2Fwa1XIJ6NmiA%2Fmqdefault.jpg)
9:41
![Adam Gleave - AI in 2025: Faster Progress, Harder Problems [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FexCu5H-6PHg%2Fmqdefault.jpg)
22:58
![Sam Bowman - Lessons Learned from the First Misalignment Safety Case [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FeO7RWlUl1BE%2Fmqdefault.jpg)
9:51
10:18
![Neel Nanda - Our Pivot To Pragmatic Interpretability [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2Fk93o4R145Os%2Fmqdefault.jpg)
10:20
![Anka Reuel - How do we know what AI can (and can't) do? [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FppDX_OGrj48%2Fmqdefault.jpg)
10:01
53:27
![Yoshua Bengio - An Argument for the Safety of Scientist Al [UK AISI Alignment Conference]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2Ff68RJ7CAqxE%2Fmqdefault.jpg)
21:30
![Alex Bores - How the States Should Regulate AI [Journalism Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FaCU-RXC65Gs%2Fmqdefault.jpg)
30:58
![Adam Gleave - Misalignment [Journalism Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FGihWL1L2vGY%2Fmqdefault.jpg)
9:38
48:21
54:29
![Sarah Cen - AI Supply Chains: An Emerging Ecosystem of AI Dependencies [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FTqc9AXjHVhQ%2Fmqdefault.jpg)
9:17
5:32
![Hamza Chaudhry - AI-Military Integration Under President Trump [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FCwVCWqQmPfQ%2Fmqdefault.jpg)
5:41
![Tina Morrison - Verifiable Compute & Building Trust in Agentic Supply Chains [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FUB3Vilf2gD4%2Fmqdefault.jpg)
5:28
53:46
![Steve Kelly - National Security & Defense [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FrCs2fcHBS5g%2Fmqdefault.jpg)
10:07
![Olivia Shoemaker - Sandpaper Socks: Operational Considerations in AI Evals [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FJEi9xCYGUnE%2Fmqdefault.jpg)
5:12
![Ben Bucknall - An Overview of Technical AI Governance [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2Fw7YX71viud8%2Fmqdefault.jpg)
20:33
![Mary Phuong - AI Control: Addressing Risks from Agentic Internal Deployments [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FRS6UyRXKnqs%2Fmqdefault.jpg)
15:16
![Daniel Kang - CVE-Bench [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FLXCM505db8A%2Fmqdefault.jpg)
4:27
33:19
![Miranda Bogen - Making Sense of the AI Auditing Ecosystem [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FbTwsvANw1oA%2Fmqdefault.jpg)
17:12
![Robert Trager - Prioritizing Technical Governance Investments: Verification [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FdTaLbZQ68DU%2Fmqdefault.jpg)
5:30
![Charles Yang - Hydropower: the Missing Piece [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FDbqQmuQMHog%2Fmqdefault.jpg)
12:51
![Fatemeh Ganji - Application of Cryptographic Primitives in AI Accelerators [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FHvTyPzmZU4g%2Fmqdefault.jpg)
6:30
![Kevin Wei - Policy-Oriented AI Evaluations [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FIHIxzs3gV0o%2Fmqdefault.jpg)
7:46
![Ben Cottier - Rising Cost of Evaluations, Falling Cost of Intelligence [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FL88fk0qPWWA%2Fmqdefault.jpg)
3:43
49:07
![Baoyuan Wu - Unthinking Vulnerability of Large Reasoning Models [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2F0ugOU8gwQaA%2Fmqdefault.jpg)
4:36
![Huiqi Deng - Unified Explanation of DNN Inference Logic & Representation [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FxcU9lZ0QcXI%2Fmqdefault.jpg)
5:28
![Cassidy Laidlaw - A New Definition & Improved Mitigation for Reward Hacking [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2Fs_I-6AJfz58%2Fmqdefault.jpg)
5:15
![Animesh Mukherjee - Safety Alignment of LLMs [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2F_yspjAG423M%2Fmqdefault.jpg)
5:57
![Sara McNaughton - AI National Security Policy: Industry and Government [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FCS9i3JWffww%2Fmqdefault.jpg)
5:39
![Arnab Datta - Compute in America: Playbook for Secure Clusters at Home [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FAYKJdB5pMiQ%2Fmqdefault.jpg)
10:10
![Onni Aarne - Hardware-Enabled Verifiability as a Data Center Security Property [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FAvWCwprC3A4%2Fmqdefault.jpg)
5:14
![Asad Ramzanali - Normal Policy Tools for a Normal Technology [Technical AI Policy]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FdDQMXpe_9XM%2Fmqdefault.jpg)
5:37
![Yoshua Bengio - AI Catastrophic Risks & Scientist AI Solution [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FSvrVKZhMDLw%2Fmqdefault.jpg)
42:02
![Jiaming Ji - Deceptive Alignment & Thinking Monitor in LLMs [Alignment Workshop]](/thumb?url=http%3A%2F%2Finvidious%3A3000%2Fvi%2FRvFnZJaSCBA%2Fmqdefault.jpg)
4:34