Understanding AI World Models w/ Chris Canal
Chris Canal, co-founder of EquiStamp, joins muckrAIkers as our first ever podcast guest! In this ~3.5 hour interview, we discuss intelligence vs. competencies, the importance of test-time compute, moving goalposts, the orthogonality thesis, and much more.
A seasoned software developer, Chris started EquiStamp as a way to improve our current understanding of model failure modes and capabilities in late 2023. Now a key contractor for METR, EquiStamp evaluates the next generation of LLMs from frontier model developers like OpenAI and Anthropic.
EquiStamp is hiring, so if you're a software developer interested in a fully remote opportunity with flexible working hours, join the EquiStamp Discord server and message Chris directly; oh, and let him know muckrAIkers sent you!
Links
EquiStamp is hiring, so if you're a software developer interested in a fully remote opportunity with flexible working hours, join the EquiStamp Discord server and message Chris directly; oh, and let him know muckrAIkers sent you!
- (00:00) - Recording date
- (00:05) - Intro
- (00:29) - Hot off the press
- (02:17) - Introducing Chris Canal
- (19:12) - World/risk models
- (35:21) - Competencies + decision making power
- (42:09) - Breaking models down
- (01:05:06) - Timelines, test time compute
- (01:19:17) - Moving goalposts
- (01:26:34) - Risk management pre-AGI
- (01:46:32) - Happy endings
- (01:55:50) - Causal chains
- (02:04:49) - Appetite for democracy
- (02:20:06) - Tech-frame based fallacies
- (02:39:56) - Bringing back real capitalism
- (02:45:23) - Orthogonality Thesis
- (03:04:31) - Why we do this
- (03:15:36) - Equistamp!
Links
- EquiStamp
- Chris's Twitter
- METR Paper - RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts
- All Trades article - Learning from History: Preventing AGI Existential Risks through Policy by Chris Canal
- Better Systems article - The Omega Protocol: Another Manhattan Project
Superintelligence & Commentary
- Wikipedia article - Superintelligence: Paths, Dangers, Strategies by Nick Bostrom
- Reflective Altruism article - Against the singularity hypothesis (Part 5: Bostrom on the singularity)
- Into AI Safety Interview - Scaling Democracy w/ Dr. Igor Krawczuk
Referenced Sources
- Book - Man-made Catastrophes and Risk Information Concealment: Case Studies of Major Disasters and Human Fallibility
- Artificial Intelligence Paper - Reward is Enough
- Wikipedia article - Capital and Ideology by Thomas Piketty
- Wikipedia article - Pantheon
LeCun on AGI
- "Won't Happen" - Time article - Meta’s AI Chief Yann LeCun on AGI, Open-Source, and AI Risk
- "But if it does, it'll be my research agenda latent state models, which I happen to research" - Meta Platforms Blogpost - I-JEPA: The first AI model based on Yann LeCun’s vision for more human-like AI
Other Sources
- Stanford CS Senior Project - Timing Attacks on Prompt Caching in Language Model APIs
- TechCrunch article - AI researcher François Chollet founds a new AI lab focused on AGI
- White House Fact Sheet - Ensuring U.S. Security and Economic Strength in the Age of Artificial Intelligence
- New York Post article - Bay Area lawyer drops Meta as client over CEO Mark Zuckerberg’s ‘toxic masculinity and Neo-Nazi madness’
- OpenEdition Academic Review of Thomas Piketty
- Neural Processing Letters Paper - A Survey of Encoding Techniques for Signal Processing in Spiking Neural Networks
- BFI Working Paper - Do Financial Concerns Make Workers Less Productive?
- No Mercy/No Malice article - How to Survive the Next Four Years by Scott Galloway
Creators and Guests
