Mantas Mazeika - Tamper-Resistant Safeguards for LLMs [Alignment Workshop]
5:22
Mantas Mazeika - Tamper-Resistant Safeguards for LLMs [Alignment Workshop]
12 сағат бұрын
Evan Hubinger - Alignment Stress-Testing at Anthropic [Alignment Workshop]
5:26
Evan Hubinger - Alignment Stress-Testing at Anthropic [Alignment Workshop]
14 сағат бұрын
Richard Ngo - Reframing AGI Threat Models [Alignment Workshop]
5:44
Richard Ngo - Reframing AGI Threat Models [Alignment Workshop]
16 сағат бұрын
Julian Michael - Empirical Progress on Debate [Alignment Workshop]
12:40
Julian Michael - Empirical Progress on Debate [Alignment Workshop]
Күн бұрын
Micah Carroll - Targeted Manipulation & Deception in LLMs [Alignment Workshop]
12:48
Micah Carroll - Targeted Manipulation & Deception in LLMs [Alignment Workshop]
Күн бұрын
Adam Gleave - Will Scaling Solve Robustness? [Alignment Workshop]
11:47
Adam Gleave - Will Scaling Solve Robustness? [Alignment Workshop]
Күн бұрын
Alex Wei - Paradigms & Robustness [Alignment Workshop]
11:44
Alex Wei - Paradigms & Robustness [Alignment Workshop]
14 күн бұрын
Stephen Casper - Powering Up Capability Evaluations [Alignment Workshop]
13:00
Stephen Casper - Powering Up Capability Evaluations [Alignment Workshop]
14 күн бұрын
Andy Zou - Top-Down Interpretability for AI Safety [Alignment Workshop]
19:08
Andy Zou - Top-Down Interpretability for AI Safety [Alignment Workshop]
14 күн бұрын
Atticus Geiger - State of Interpretability & Ideas for Scaling Up [Alignment Workshop]
21:14
Atticus Geiger - State of Interpretability & Ideas for Scaling Up [Alignment Workshop]
14 күн бұрын
Kwan Yee Ng - AI Policy in China [Alignment Workshop]
8:53
Kwan Yee Ng - AI Policy in China [Alignment Workshop]
14 күн бұрын
Anca Dragan - Optimized Misalignment [Alignment Workshop]
40:39
Anca Dragan - Optimized Misalignment [Alignment Workshop]
21 күн бұрын
Buck Shlegeris - AI Control [Alignment Workshop]
29:44
Buck Shlegeris - AI Control [Alignment Workshop]
21 күн бұрын
Beth Barnes - METR Updates & Research Directions [Alignment Workshop]
23:14
Beth Barnes - METR Updates & Research Directions [Alignment Workshop]
21 күн бұрын
FAR.Research: Planning in a recurrent neural network that plays Sokoban
2:16
FAR.Research: Planning in a recurrent neural network that plays Sokoban
Ай бұрын
Andrew Freedman - Campaigns in Emerging Issues: Lessons Learned from the Field
56:18
Andrew Freedman - Campaigns in Emerging Issues: Lessons Learned from the Field
2 ай бұрын
Stephen Casper - Generalized Adversarial Training and Testing
5:25
Stephen Casper - Generalized Adversarial Training and Testing
3 ай бұрын
Neel Nanda - Mechanistic Interpretability: A Whirlwind Tour
21:32
Neel Nanda - Mechanistic Interpretability: A Whirlwind Tour
3 ай бұрын
Nicholas Carlini - Some Lessons from Adversarial Machine Learning
16:29
Nicholas Carlini - Some Lessons from Adversarial Machine Learning
3 ай бұрын
Vincent Conitzer - Game Theory and Social Choice for Cooperative AI
5:17
Vincent Conitzer - Game Theory and Social Choice for Cooperative AI
3 ай бұрын
Mary Phuong - Dangerous Capability Evals: Basis for Frontier Safety
15:16
Mary Phuong - Dangerous Capability Evals: Basis for Frontier Safety
3 ай бұрын
Zhaowei Zhang - Research Proposal: The 3-Layer Paradigm for Implementing Sociotechnical AI Alignment
5:08
Zhaowei Zhang - Research Proposal: The 3-Layer Paradigm for Implementing Sociotechnical AI Alignment
3 ай бұрын
Vienna Alignment Workshop Panel Discussion - Current Issues in AI Safety
44:37
Vienna Alignment Workshop Panel Discussion - Current Issues in AI Safety
3 ай бұрын
Aditya Gopalan - Towards Reliable Alignment: Uncertainty-Aware RLHF
5:25
Aditya Gopalan - Towards Reliable Alignment: Uncertainty-Aware RLHF
3 ай бұрын
Vikrant Varma - Challenges With Unsupervised LLM Knowledge Discovery
6:31
Vikrant Varma - Challenges With Unsupervised LLM Knowledge Discovery
3 ай бұрын
Jan Leike - Supervising AI on hard tasks
33:35
Jan Leike - Supervising AI on hard tasks
3 ай бұрын
Oliver Klingefjord - What are Human Values, and How Do We Align AI to Them?
4:20
Oliver Klingefjord - What are Human Values, and How Do We Align AI to Them?
3 ай бұрын
Sophie Bridgers - Scalable Oversight: A Rater Assist Approach
5:39
Sophie Bridgers - Scalable Oversight: A Rater Assist Approach
3 ай бұрын
Alex Tamkin - Measuring and Improving Human Agency in a World of AI Agents
5:37
Alex Tamkin - Measuring and Improving Human Agency in a World of AI Agents
3 ай бұрын
Пікірлер