
AXRP - the AI X-risk Research Podcast 20 - 'Reform' AI Alignment with Scott Aaronson
18 snips
Apr 12, 2023 Scott Aaronson discusses how to think scientifically about AI risk, the challenge of aligning potentially deceptive systems, and the role of democratic oversight. He explains his work on watermarking AI-generated text and cryptographic backdoors, and reflects on moving from quantum computing to AI safety.
AI Snips
Chapters
Transcript
Episode notes
Use Concentration Of Power To Deploy Safety Standards
- When few players control state-of-the-art models, push for industry-wide technical mitigations (e.g., watermarking) to become standards.
- Aaronson notes high training costs give a window where convincing leading labs can achieve broad effect.
Focus On Detecting Model Origin As A Tractable Defense
- Aaronson anticipated mass misuse patterns (impersonation, essay cheating, propaganda) and focused on detecting model-origin as a tractable defensive target.
- He pivoted from abstract alignment to watermarking because it yields provable, implementable defenses for current harms.
Undetectable Watermarking Without Quality Loss
- A statistical watermark can be inserted by pseudorandomly biasing token sampling without degrading output quality.
- Aaronson gives a simple rule using pseudorandom scores r_i and model probabilities p_i so sampling remains statistically identical yet detectable later.

