Castuner
Submit a podcast

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

Podcast website

Listen in your app

Episodes

250 episodes

  1. “Free-Floating Social Patterns” by johnswentworth 22:35
  2. “Against Against SURA” by Mikhail Samin 26:45
  3. “Magma is partnering with CAISSI to investigate recent unintended model behavior” by Parv Mahajan 5:40
  4. “Accidentally Misleading People Should Be Embarrassing; Or, Higher Innocence” by Zack_M_Davis 11:06
  5. “Towards The Autograntor” by Scott Alexander 55:34
  6. “Misalignment traps lie in wait” by David Africa 6:17
  7. “Explaining “AI might obliterate you” to senior policymakers in India” by TurnTrout 24:35
  8. “Generalized belief states in transformers” by Artemy Kolchinsky 41:01
  9. “Against SURA” by Scott Alexander 52:30
  10. “What Social Constructs Are (And Are Not)” by johnswentworth 5:56
  11. “Reviewing my 2017 AI Risk Project” by jefftk 11:51
  12. “Childhood and Education #22: Voice Without Exit” by Zvi 45:16
  13. “Dice enterprises as imperfect-recall games” by jessicata 22:50
  14. “Lessons From Red-teaming Auto-review, OpenAI’s Blocking Monitor” by monika_j, Giovanni M. Occhipinti 29:24
  15. “Microdosing the spirit of Anthropic” by Jan_Kulveit 9:36
  16. “Walking Partway to School” by jefftk 1:16
  17. “My experiences with the extremes of post-viral illness and brain retraining/mindbody work” by riceissa 1:53:07
  18. “What is OpenAI’s Mission Advisory Council?” by hersheys, meru 2:26
  19. “Making alignment the agent’s problem” by Florian_Dietz 8:57
  20. “AI #192: Anthropic Is Going Public” by Zvi 1:48:42
  21. “Leaking Muse’s Charter, Meta’s model spec” by vigji 13:35
  22. “Three Villages in a Trenchcoat, Post I” by DaystarEld 36:18
  23. [Linkpost] “Reconceptualize things as your top affordances” by KatjaGrace 2:05
  24. “You can now ”@Grok” on LessWrong” by Ruby 3:26
  25. “The Crypto Dream is Structurally Illegal” by Taylor G. Lunt 10:43
  26. “Some thoughts on GRAFT and follow-up work” by shawnghu 3:29
  27. “Subtly wrong advice misaligns models more than obviously wrong advice” by Christine Corry, arav-dhoot, Jozdien 22:37
  28. “Anthropic Files Its S-1” by Zvi 1:17:45
  29. “I spent 12 hours writing an article for LessWrong, calling for a more ‘hippie’ rationalism. Then I didn’t post it. This is why (plus a link to the article, explicitly not located on LessWrong)” by honeybee 8:29
  30. “Streetlight, Torchlight and Nightvision” by DusanDNesic 11:57
  31. “Quantity has a quality of its own” by djbinder 11:35
  32. “Against Girardian mimesis” by Viliam 13:10
  33. “Anthropic Versus Anthropic” by Zvi 48:44
  34. “AI speeds up 3rd party safety researchers by ~1.6x (via self-reports)” by Angel Martinez, Dewi Gould, nicole x, Alejandro Aristizabal 15:32
  35. “A big case study of propensity entanglement” by nielsrolf, lwen2027, megasilverfist, Owen Terry, Johannes Taraz 5:39
  36. “Scattered thoughts on how doing math feels these days” by dynomight 15:40
  37. “Measuring agent capabilities on open-ended AI R&D tasks” by Alex Jackson, Titus Buckworth, Jason R Brown, Francis Rhys Ward 36:20
  38. “The AI buildout is the largest bet in the history of capitalism. Key decision makers believe very powerful AI will be achieved soon.” by Hayekstan 7:22
  39. “Hair Thickness of My Friends” by XelaP 6:35
  40. “A basic case for differentially accelerating conceptual reasoning capabilities” by Emery Cooper, Caspar Oesterheld, Chi Nguyen 50:07
  41. “A cat-belling problem for FDT” by jessicata 20:24
  42. “Anthropic are the Good Guys” by Ivan Vendrov 20:55
  43. “Some Memories of Early Anthropic” by Ivan Vendrov 16:44
  44. “Is GPT 2XL already clean?” by Jasper Blank 12:26
  45. “LoReFT GRAFT Better at Preventing RL Grift” by Samuel Knoche 8:14
  46. “A Study of China Does Not Personal Experience Make” by celesteli 8:30
  47. “San Francisco State University in Twilight” by Zack_M_Davis 16:16
  48. “From overeliciting to undereliciting LLM propensities in just a few months” by David Africa 3:39
  49. “Control monitors need alignment assessments too” by Fabien Roger 7:42
  50. “Fermi Poker” by Novalis, Screwtape 11:40