Castuner

LessWrong (Curated & Popular)

LessWrong

Audio narrations of LessWrong posts. Includes all curated posts and all posts with 125+ karma. If you'd like more, subscribe to the “Lesswrong (30+ karma)” feed.

Strona podcastu

Słuchaj w swojej aplikacji

Odcinki

1 078 odcinków

  1. [Linkpost] "AIFP: Looks Like the Intelligence Explosion Will Happen in 2027 After All" by Zach Stein-Perlman 2:17
  2. "Fable 5.2 is Very, Very Paranoid" by peralice 5:36
  3. "We don’t understand whether GDM intentionally trains on CoT" by Alek Westover, Buck 10:48
  4. "Modern LLMs Don’t Know What Yudkowsky and Soares Think of Them" by N8 Programs 22:11
  5. "Have you considered Actually Trying?" by Michaël Trazzi 12:08
  6. "Lightcone Commons: Round 1 complete, Round 2 underway!" by habryka 5:18
  7. "Preservation can save the world!" by Aurelia 22:04
  8. "Epistemic Sudden Death" by Raemon 19:56
  9. "Our Most Aligned Model Yet" by Edward James Young 4:20
  10. "“Hardwired Pause” should likely be your favorite (pause) plan." by David Scott Krueger 14:43
  11. "Live disagreements with people around me" by KatjaGrace 5:41
  12. "Where is all the AI safety research uplift?" by Buck 6:02
  13. "Near Horizons" by David Africa 10:33
  14. "Elegy for What’s Left of the Normal" by Jo Jiao 8:11
  15. "Five Types of “Corrigibility Projects” I Don’t Want to Fund" by Max Harms 10:41
  16. "Hilarity ensues" by Malmesbury 17:13
  17. "We urgently need to practice before we can pause" by Nikola Jurkovic 12:59
  18. "“Illegible problems” as the 2027 political boss fight" by Raemon 16:52
  19. "Organizations I’d recommend for funding" by So8res 8:06
  20. "People Should Resolve Tensions In AI Safety Research" by David Africa 10:14
  21. [Linkpost] "METR: Independent Assessment of AI R&D Acceleration at Anthropic in October 2026" by Zach Stein-Perlman 4:58
  22. "Help your friends get ADHD and depression meds" by Raemon 0:55
  23. "Towards The Autograntor" by Scott Alexander 55:33
  24. [Linkpost] "OpenAI: Astra covertly underperforms on safety research" by Zach Stein-Perlman 3:41
  25. "Towards understanding score-seeking in LLMs" by Alex Mallen, Aghyad Deeb, ryan_greenblatt 19:19
  26. "Against strawmanning unilateral pauses" by Geoffrey Irving 14:09
  27. "Explaining “AI might obliterate you” to senior policymakers in India" by TurnTrout 24:35
  28. "Scott Alexander’s Against SURA Seems Deeply Confused" by Zvi 1:06:41
  29. "Leaking Muse’s Charter, Meta’s model spec" by vigji 13:35
  30. "Against SURA" by Scott Alexander 52:30
  31. "Microdosing the spirit of Anthropic" by Jan_Kulveit 9:35
  32. "My experiences with the extremes of post-viral illness and brain retraining/mindbody work" by riceissa 1:53:07
  33. "Three Villages in a Trenchcoat, Post I" by DaystarEld 36:18
  34. "You can now ”@Grok” on LessWrong" by Ruby 3:25
  35. "San Francisco State University in Twilight" by Zack_M_Davis 16:16
  36. "Scattered thoughts on how doing math feels these days" by dynomight 15:40
  37. "From overeliciting to undereliciting LLM propensities in just a few months" by David Africa 3:39
  38. "Anthropic are the Good Guys" by Ivan Vendrov 20:55
  39. "Some Memories of Early Anthropic" by Ivan Vendrov 16:44
  40. "Greater good arguments in AI safety" by Dean Valentine 7:15
  41. "Wah wah wah wah do more AI R&D" by TsviBT 10:01
  42. "Why I’m becoming a professor in AI safety in Beijing" by Buddenbroke 18:11
  43. "A brief(ish) introduction to LM psychology" by Raymond Douglas, Jan_Kulveit 47:06
  44. "There Will Be Hells" by Stephen Martin 14:25
  45. [Linkpost] "huggingface.wtf, an accessible but complete explanation" by Raemon 3:23
  46. "Gradient Routing Localizes and Removes Unintended Behaviors in RL" by shawnghu, Jake Ward, ariaw, Nathan Hu, Bryce Woodworth, TurnTrout, cloud 13:14
  47. [Linkpost] "Capital Ownership Will Make You Go Crazy First" by Jan_Kulveit 4:48
  48. "I Did This Without Your Knowledge" by joec 1:22:19
  49. "Neural networks are not already clean" by leogao 7:07
  50. "GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behavior" by Axel Højmark, Ezra Newman 26:54