A Semitechnical Introductory Dialogue on Solomonoff Induction — AI Alignment Forum
(Originally posted in December 2015: A dialogue between Ashley, a computer scientist who's never heard of Solomonoff's theory of inductive inference, and Blaine, who thinks it is the best thing since sliced bread.) ASHLEY: Good evening, Msr. Blaine. BLAINE: Good evening, Msr. Ashley. ASHLEY: I've heard there's this thing called "Solomonoff's theory of inductive inference". BLAINE: The rumors have spread, then. ASHLEY: Yeah, so, what the heck is that about? BLAINE: Invented in the 1960s by the mathematician Ray Solomonoff, the key idea in Solomonoff induction is to do sequence prediction by using Bayesian updating on a prior composed of a mixture of all computable probability distributions— ASHLEY: Wait. Back up a lot. Before you try to explain what Solomonoff induction is, I'd like you to try to tell me what it does, or why people study it in the first place. I find that helps me organize my listening. Right now I don't even know why I should be interested in this. BLAINE: Um,
x A Semitechnical Introductory Dialogue on Solomonoff Induction — AI Alignment Forum Solomonoff induction Occam's Razor Dialogue (format) AI Rationality World Modeling Curated 33 A Semitechnical Introductory Dialogue on Solomonoff Induction by Eliezer Yudkowsky 4th Mar 2021 65 min read 32 33 ( Originally posted in December 2015: A dialogue between Ashley, a computer scientist who's never heard of Solomonoff's theory of inductive inference , and Blaine, who thinks it is the best thing since sliced bread. ) i. Unbounded analysis ASHLEY: Good evening, Msr. Blaine. BLAINE: Good evening, Msr. Ashle
related reading
- A Semitechnical Introductory Dialogue on Solomonoff Induction — LessWronglesswrong.com
- Solomonoff's theory of inductive inference - Wikipediaen.wikipedia.org
- An Intuitive Explanation of Solomonoff Induction — LessWronglesswrong.com
- The Solomonoff Prior is Malign — LessWronglesswrong.com
- Ray Solomonoff - Wikipediaen.wikipedia.org
- Probabilities are not the right concept — LessWronglesswrong.com
- Yudhister Kumaryudhister.me
- A Technical Introduction to Solomonoff Induction without K-Complexity — LessWronglesswrong.com
- Common Knowledge and Aumann’s Agreement Theoremscottaaronson.blog
- John Schulman - Reinforcement Learning from Human Feedback: Progress and Challengesyoutube.com
- In (highly contingent!) defense of interpretability-in-the-loop ML training — AI Alignment Forumalignmentforum.org
- Towards a Formal Scientific Epistemologymindthefuture.info