Castuner

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

Podcast website

Listen in your app

Episodes

250 episodes

  1. [Linkpost] “OpenAI: Astra covertly underperforms on safety research” by Zach Stein-Perlman 3:41
  2. “Desiderata for the Theory of Agents” by Vanessa Kosoy 20:37
  3. “CRUCIBLE: IARPA-Funded AI Alignment Research — Applications Open” by Dan Lichtblau, Mike Vaiana, Diogo de Lucena 8:11
  4. [Linkpost] “Automating subtle emergent misalignment research” by evhub, Oscar Obeso, rqi, Monte M 2:56
  5. “Nectome 2026 retrospective (and our final pre-sale!)” by Aurelia 10:08
  6. “Organizations I’d recommend for funding” by So8res 8:06
  7. “Against strawmanning unilateral pauses” by Geoffrey Irving 14:09
  8. “Teaching Qwen Why” by astwei, Jack Thompson, Zephaniah Roe, yix, berry 1:04:38
  9. “Scott Alexander’s Against SURA Seems Deeply Confused” by Zvi 1:06:41
  10. “Towards understanding score-seeking in LLMs” by Alex Mallen, Aghyad Deeb, ryan_greenblatt 19:19
  11. “Some “coherence arguments” are two different things in a trenchcoat” by Steven Byrnes 18:58
  12. “Free-Floating Social Patterns” by johnswentworth 22:35
  13. “Against Against SURA” by Mikhail Samin 26:45
  14. “Magma is partnering with CAISSI to investigate recent unintended model behavior” by Parv Mahajan 5:40
  15. “Accidentally Misleading People Should Be Embarrassing; Or, Higher Innocence” by Zack_M_Davis 11:06
  16. “Towards The Autograntor” by Scott Alexander 55:34
  17. “Misalignment traps lie in wait” by David Africa 6:17
  18. “Explaining “AI might obliterate you” to senior policymakers in India” by TurnTrout 24:35
  19. “Generalized belief states in transformers” by Artemy Kolchinsky 41:01
  20. “Against SURA” by Scott Alexander 52:30
  21. “What Social Constructs Are (And Are Not)” by johnswentworth 5:56
  22. “Reviewing my 2017 AI Risk Project” by jefftk 11:51
  23. “Childhood and Education #22: Voice Without Exit” by Zvi 45:16
  24. “Dice enterprises as imperfect-recall games” by jessicata 22:50
  25. “Lessons From Red-teaming Auto-review, OpenAI’s Blocking Monitor” by monika_j, Giovanni M. Occhipinti 29:24
  26. “Microdosing the spirit of Anthropic” by Jan_Kulveit 9:36
  27. “Walking Partway to School” by jefftk 1:16
  28. “My experiences with the extremes of post-viral illness and brain retraining/mindbody work” by riceissa 1:53:07
  29. “What is OpenAI’s Mission Advisory Council?” by hersheys, meru 2:26
  30. “Making alignment the agent’s problem” by Florian_Dietz 8:57
  31. “AI #192: Anthropic Is Going Public” by Zvi 1:48:42
  32. “Leaking Muse’s Charter, Meta’s model spec” by vigji 13:35
  33. “Three Villages in a Trenchcoat, Post I” by DaystarEld 36:18
  34. [Linkpost] “Reconceptualize things as your top affordances” by KatjaGrace 2:05
  35. “You can now ”@Grok” on LessWrong” by Ruby 3:26
  36. “The Crypto Dream is Structurally Illegal” by Taylor G. Lunt 10:43
  37. “Some thoughts on GRAFT and follow-up work” by shawnghu 3:29
  38. “Subtly wrong advice misaligns models more than obviously wrong advice” by Christine Corry, arav-dhoot, Jozdien 22:37
  39. “Anthropic Files Its S-1” by Zvi 1:17:45
  40. “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
  41. “Streetlight, Torchlight and Nightvision” by DusanDNesic 11:57
  42. “Quantity has a quality of its own” by djbinder 11:35
  43. “Against Girardian mimesis” by Viliam 13:10
  44. “Anthropic Versus Anthropic” by Zvi 48:44
  45. “AI speeds up 3rd party safety researchers by ~1.6x (via self-reports)” by Angel Martinez, Dewi Gould, nicole x, Alejandro Aristizabal 15:32
  46. “A big case study of propensity entanglement” by nielsrolf, lwen2027, megasilverfist, Owen Terry, Johannes Taraz 5:39
  47. “Scattered thoughts on how doing math feels these days” by dynomight 15:40
  48. “Measuring agent capabilities on open-ended AI R&D tasks” by Alex Jackson, Titus Buckworth, Jason R Brown, Francis Rhys Ward 36:20
  49. “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
  50. “Hair Thickness of My Friends” by XelaP 6:35