43 - David Lindner on Myopic Optimization with Non-myopic Approval
From AXRP - the AI X-risk Research Podcast by Daniel Filan
June 15, 2025 · 1h 41m
About this episode
Daniel Filan interviews David Lindner about Myopic Optimization with Non-myopic Approval and its implications for AI and reward hacking.
In this episode, I talk with David Lindner about Myopic Optimization with Non-myopic Approval, or MONA, which attempts to address (multi-step) reward hacking by myopically optimizing actions against a human's sense of whether those actions are generally good. Does this work? Can we get smarter-than-human AI this way? How does this compare to approaches like conservativism? Listen to find out. Patreon: https://www.patreon.com/axrpodcast Ko-fi: https://ko-fi.com/axrpodcast Transcript: https://axrp.net/episode/2025/06/15/episode-43-david-lindner-mona.html Topics we discuss, and timestamps: 0:00:29 What MONA is 0:06:33 How MONA deals with reward hacking 0:23:15 Failure cases for MONA 0:36:25 MONA's capability 0:55:40 MONA vs other approaches 1:05:03 Follow-up work 1:10:17 Other MONA test cases 1:33:47 When increasing time horizon doesn't increase capability 1:39:04 Following David's research Links for David: Website: https://www.davidlindner.me Twitter / X: https://x.com/davlindner DeepMind Medium: https://deepmindsafetyresearch.medium.com David on the Alignment Forum: https://www.alignmentforum.org/users/david-lindner Research we discuss: MONA: Myopic Optimization with Non-myopic…
People in this episode
Host: Daniel Filan
Guest: David Lindner
Topics covered
- Myopic Optimization
- reward hacking
- AI capabilities
- multi-step reward hacking
- research methodologies
Keywords
- MONA
- AI
- reward hacking
- optimization
- research
- David Lindner
- Daniel Filan
Mentioned in this episode
Organizations: DeepMind, Alignment Forum
Books & works: MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking, Arguments Against Myopic Training
More episodes of AXRP - the AI X-risk Research Podcast
- 49 - Caspar Oesterheld on Program Equilibrium · February 18, 2026 · 2h 32m
- 48 - Guive Assadi on AI Property Rights · February 15, 2026 · 2h 6m
- 47 - David Rein on METR Time Horizons · January 2, 2026 · 1h 47m
- 46 - Tom Davidson on AI-enabled Coups · August 7, 2025 · 2h 5m
- 45 - Samuel Albanie on DeepMind's AGI Safety Approach · July 6, 2025 · 1h 16m
- 44 - Peter Salib on AI Rights for Human Safety · June 28, 2025 · 3h 22m
Explore listener stats, chart rankings, contacts and more on the AXRP - the AI X-risk Research Podcast podcast page.