AXRP Episode 9 - Finite Factored Sets with Scott Garrabrant - LessWrong

Google Podcasts link • This podcast is called AXRP, pronounced axe-urp and short for the AI X-risk Research Podcast. Here, I (Daniel Filan) have conversations with researchers about their papers. We…

x AXRP Episode 9 - Finite Factored Sets with Scott Garrabrant — LessWrong Finite Factored Sets Abstraction Causality Embedded Agency Finite Factored Sets Interviews Audio AXRP AI Curated 59 AXRP Episode 9 - Finite Factored Sets with Scott Garrabrant by DanielFilan 24th Jun 2021 AXRP AI Alignment Forum 70 min read 2 59 Ω 34 YouTube link This podcast is called AXRP, pronounced axe-urp and short for the AI X-risk Research Podcast. Here, 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 migh

related reading

• Finite Factored Sets — LessWronglesswrong.com
• Finite Factored Sets — AI Alignment Forumalignmentforum.org
• LessWronglesswrong.com
• Finite Factored Sets — LessWronglesswrong.com
• 32 - Understanding Agency with Jan Kulveit | AXRP - the AI X-risk Research Podcastaxrp.net
• What Would I Do? Self-prediction in Simple Algorithms — LessWronglesswrong.com
• Counterfactability — LessWronglesswrong.com
• Shtetl-Optimized >> Blog Archive >> My podcast with Dan Faggellascottaaronson.blog
• 39 - Evan Hubinger on Model Organisms of Misalignment | AXRP - the AI X-risk Research Podcastaxrp.net
• Saving Time — AI Alignment Forumalignmentforum.org
• Embedded Agency (full-text version) — LessWronglesswrong.com
• Neel Nanda on Mechanistic Interpretability: Progress, Limits, and Paths to Safer AI — EA Forumforum.effectivealtruism.org