Can Defense in Depth Work for AI?
Adam Gleave, CEO of FAR.AI, discusses post-AGI scenarios, risks of gradual disempowerment, defense-in-depth safety strategies, scalable oversight for AI deception, and the challenges of interpretability, as well as FAR.AI's integrated research and policy work.
Watch Episode Here
Listen to Episode Here
Show Notes
Adam Gleave is co-founder and CEO of FAR.AI. In this cross-post from The Cognitive Revolution Podcast, he joins to discuss post-AGI scenarios and AI safety challenges. The conversation explores his three-tier framework for AI capabilities, gradual disempowerment concerns, defense-in-depth security, and research on training less deceptive models. Topics include timelines, interpretability limitations, scalable oversight techniques, and FAR.AI’s vertically integrated approach spanning technical research, policy advocacy, and field-building.
LINKS:
Adam Gleave - https://www.gleave.me
FAR.AI - https://www.far.ai
The Cognitive Revolution Podcast - https://www.cognitiverevolution.ai
PRODUCED BY:
https://aipodcast.ing
CHAPTERS:
(00:00) A Positive Post-AGI Vision
(10:07) Surviving Gradual Disempowerment
(16:34) Defining Powerful AIs
(27:02) Solving Continual Learning
(35:49) The Just-in-Time Safety Problem
(42:14) Can Defense-in-Depth Work?
(49:18) Fixing Alignment Problems
(58:03) Safer Training Formulas
(01:02:24) The Role of Interpretability
(01:09:25) FAR.AI's Vertically Integrated Approach
(01:14:14) Hiring at FAR.AI
(01:16:02) The Future of Governance
SOCIAL LINKS:
Website: https://podcast.futureoflife.org
Twitter (FLI): https://x.com/FLI_org
Twitter (Gus): https://x.com/gusdocker
LinkedIn: https://www.linkedin.com/company/future-of-life-institute/
YouTube: https://www.youtube.com/channel/UC-rCCy3FQ-GItDimSR9lhzw/
Apple: https://geo.itunes.apple.com/us/podcast/id1170991978
Spotify: https://open.spotify.com/show/2Op1WO3gwVwCrYHg4eoGyP