))
Sleeper Agents | Evan Hubinger | EA Global Bay Area: 2024
Manage episode 404913498 series 3503936
Content provided by Aaron Bergman. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Aaron Bergman or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://player.fm/legal.
If an AI system learned a deceptive strategy, could we detect it and remove it using current state-of-the-art safety training techniques? That's the question that Evan and his coauthors at Anthropic sought to answer in their work on ""Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training"", which Evan will be discussing.
Evan Hubinger leads the new Alignment Stress-Testing team at Anthropic, which is tasked with red-teaming Anthropic's internal alignment techniques and evaluations. Prior to joining Anthropic, Evan was a Research Fellow at the Machine Intelligence Research Institute and worked on a variety of theoretical alignment work, including ""Risks from Learned Optimization in Advanced Machine Learning Systems"". Evan will be talking about the Anthropic Alignment Stress-Testing team's first paper, ""Sleeper Agents: Building Deceptive LLMs that Persist Through Safety Training"".
Watch on Youtube: https://www.youtube.com/watch?v=BgfT0AcosHw
122 episodes
Share
