[Crosspost] Adam Gleave on Vulnerabilities in GPT-4 APIs (+ extra Nathan Labenz interview)
The Inside ViewShow Notes
This is a special crosspost episode where Adam Gleave is interviewed by Nathan Labenz from the Cognitive Revolution. At the end I also have a discussion with Nathan Labenz about his takes on AI.
Adam Gleave is the founder of Far AI, and with Nathan they discuss finding vulnerabilities in GPT-4's fine-tuning and Assistant PIs, Far AI's work exposing exploitable flaws in "superhuman" Go AIs through innovative adversarial strategies, accidental jailbreaking by naive developers during fine-tuning, and more.
OUTLINE
(00:00) Intro
(02:57) NATHAN INTERVIEWS ADAM GLEAVE: FAR.AI's Mission
(05:33) Unveiling the Vulnerabilities in GPT-4's Fine Tuning and Assistance APIs
(11:48) Divergence Between The Growth Of System Capability And The Improvement Of Control
(13:15) Finding Substantial Vulnerabilities
(14:55) Exploiting GPT 4 APIs: Accidentally jailbreaking a model
(18:51) On Fine Tuned Attacks and Targeted Misinformation
(24:32) Malicious Code Generation
(27:12) Discovering Private Emails
(29:46) Harmful Assistants
(33:56) Hijacking the Assistant Based on the Knowledge Base
(36:41) The Ethical Dilemma of AI Vulnerability Disclosure
(46:34) Exploring AI's Ethical Boundaries and Industry Standards
(47:47) The Dangers of AI in Unregulated Applications
(49:30) AI Safety Across Different Domains
(51:09) Strategies for Enhancing AI Safety and Responsibility
(52:58) Taxonomy of Affordances and Minimal Best Practices for Application Developers
(57:21) Open Source in AI Safety and Ethics
(1:02:20) Vulnerabilities of Superhuman Go playing AIs
(1:23:28) Variation on AlphaZero Style Self-Play
(1:31:37) The Future of AI: Scaling Laws and Adversarial Robustness
(1:37:21) MICHAEL TRAZZI INTERVIEWS NATHAN LABENZ
(1:37:33) Nathan’s background
(01:39:44) Where does Nathan fall in the Eliezer to Kurzweil spectrum
(01:47:52) AI in biology could spiral out of control
(01:56:20) Bioweapons
(02:01:10) Adoption Accelerationist, Hyperscaling Pauser
(02:06:26) Current Harms vs. Future Harms, risk tolerance
(02:11:58) Jailbreaks, Nathan’s experiments with Claude
The cognitive revolution: https://www.cognitiverevolution.ai/
Exploiting Novel GPT-4 APIs: https://far.ai/publication/pelrine2023novelapis/
Advesarial Policies Beat Superhuman Go AIs: https://far.ai/publication/wang2022adversarial/
More from The Inside View
Owain Evans is an AI Alignment researcher, research associate at the Center of Human Compatible AI at UC Berkeley, and now leading a new AI safety research group.
Ethan Perez is a Research Scientist at Anthropic, where he leads a team working on developing model organisms of misalignment.
Emil is the co-founder of palette.fm (colorizing B&W pictures with generative AI) and was previously working in deep learning for Google Arts & Culture.
Evan Hubinger leads the Alignment stress-testing at Anthropic and recently published "Sleeper Agents: Training Deceptive LLMs That Persist Through Safety Training".
Jeffrey Ladish is the Executive Director of Palisade Research which aimes so "study the offensive capabilities or AI systems today to better understand the risk of losing control to AI systems forever". He previously helped build out the information security program at Anthropic.