15 - Natural Abstractions with John Wentworth

Why does anybody care about natural abstractions? Do they somehow relate to math, or value learning? How do E. coli bacteria find sources of sugar? All these questions and more will be answered in this interview with John Wentworth, where we talk about his research plan of understanding agency via natural abstractions. Topics we discuss, and timestamps:  - 00:00:31 - Agency in E. Coli  - 00:04:59 - Agency in financial markets  - 00:08:44 - Inferring agency in real-world systems  - 00:16:11 - Selection theorems  - 00:20:22 - Abstraction and natural abstractions  - 00:32:42 - Information at a distance  - 00:39:20 - Why the natural abstraction hypothesis matters  - 00:44:48 - Unnatural abstractions used by humans?  - 00:49:11 - Probability, determinism, and abstraction  - 00:52:58 - Whence probabilities in deterministic universes?  - 01:02:37 - Abstraction and maximum entropy distributions  - 01:07:39 - Natural abstractions and impact  - 01:08:50 - Learning human values  - 01:20:47 - The shape of the research landscape  - 01:34:59 - Following John's work   The transcript: axrp.net/episode/2022/05/23/episode-15-natural-abstractions-john-wentworth.html   John on LessWrong: lesswrong.com/users/johnswentworth   Research that we discuss:  - Alignment by default - contains the natural abstraction hypothesis: alignmentforum.org/posts/Nwgdq6kHke5LY692J/alignment-by-default#Unsupervised__Natural_Abstractions  - The telephone theorem: alignmentforum.org/posts/jJf4FrfiQdDGg7uco/information-at-a-distance-is-mediated-by-deterministic  - Generalizing Koopman-Pitman-Darmois: alignmentforum.org/posts/tGCyRQigGoqA4oSRo/generalizing-koopman-pitman-darmois  - The plan: alignmentforum.org/posts/3L46WGauGpr7nYubu/the-plan  - Understanding deep learning requires rethinking generalization - deep learning can fit random data: arxiv.org/abs/1611.03530  - A closer look at memorization in deep networks - deep learning learns before memorizing: arxiv.org/abs/1706.05394  - Zero-shot coordination: arxiv.org/abs/2003.02979  - A new formalism, method, and open issues for zero-shot coordination: arxiv.org/abs/2106.06613  - Conservative agency via attainable utility preservation: arxiv.org/abs/1902.09725  - Corrigibility: intelligence.org/files/Corrigibility.pdf   Errata:  - E. coli has ~4,400 genes, not 30,000.  - A typical adult human body has thousands of moles of water in it, and therefore must consist of well more than 10 moles total.

Om Podcasten

AXRP (pronounced axe-urp) is the AI X-risk Research Podcast where I, Daniel Filan, have conversations with researchers about their papers. We discuss the paper, and hopefully get a sense of why it's been written and how it might reduce the risk of AI causing an existential catastrophe: that is, permanently and drastically curtailing humanity's future potential. You can visit the website and read transcripts at axrp.net.