Castuner

LessWrong (30+ Karma)

LessWrong

Audio narrations of LessWrong posts.

Site du podcast

Écouter dans votre application

Épisodes

250 épisodes

  1. “Lightcone Commons: Round 1 complete, Round 2 underway!” by habryka 5:18
  2. ″“Hardwired Pause” should likely be your favorite (pause) plan.” by David Scott Krueger 14:43
  3. “Three Phases of Capabilities and Alignment” by beren 26:39
  4. “Preservation can save the world!” by Aurelia 22:04
  5. “AI R&D Is Accelerating Towards Potential RSI in 2027” by Zvi 1:18:16
  6. “Where is all the AI safety research uplift?” by Buck 6:02
  7. “Astra covertly underperforming on safety research is concerning, even though it’s unlikely to be motivated by ambitious goals” by Alexa Pan 24:28
  8. “Knowledge of graders can mediate selection for grader-targeting reasoning through RL” by lennie, Edward James Young 25:39
  9. “Be less scared of overconfidence” by benkuhn 16:15
  10. “Bay Area Solstice 2026: Auditions!” by Vaniver 2:28
  11. [Linkpost] “Ajeya: AI is dramatically accelerating AI research right now” by Zach Stein-Perlman 3:00
  12. “All Interesting Behavior Is Overdetermined” by Eric Raymond 6:13
  13. “Lying and Not Lying to Kids” by jefftk 7:09
  14. “Three half-baked research ideas” by Owain_Evans 7:18
  15. “Elegy for What’s Left of the Normal” by Jo Jiao 8:11
  16. “Near Horizons” by David Africa 10:33
  17. “Raised by Our Children” by williawa 22:43
  18. “How to Run Better Research With Agent Fleets” by Joshua Fonseca Rivera 9:12
  19. ″“Illegible problems” as the 2027 political boss fight” by Raemon 16:52
  20. “Five Types of “Corrigibility Projects” I Don’t Want to Fund” by Max Harms 10:41
  21. “Hilarity ensues” by Malmesbury 17:13
  22. “GPT-6 Astra Covertly Underperforms on Safety Research Tasks” by Zvi 24:29
  23. “We urgently need to practice before we can pause” by Nikola Jurkovic 12:59
  24. “Models Don’t Stop Cheating When It’s Obvious They’re in an Alignment Test” by peralice 19:09
  25. “Higher salaries in AI safety” by Austin Chen 6:53
  26. “Humans can (almost) natively read neural network weights” by crabbix 5:14
  27. “On marrying the egregore” by jimmy 9:07
  28. “Argue about Risk Management Speed, not p(doom)” by Mass_Driver 32:54
  29. “AI #193: Progress May Dramatically Accelerate” by Zvi 59:42
  30. [Linkpost] “Where’s all the blackmail?” by KatjaGrace 1:45
  31. “Is there any compelling case that a nearterm AI halt would significantly hurt the economy?” by Raemon 4:23
  32. “Help your friends get ADHD and depression meds” by Raemon 0:55
  33. [Linkpost] “METR: Independent Assessment of AI R&D Acceleration at Anthropic in October 2026” by Zach Stein-Perlman 4:59
  34. “Efficient Lempel-Ziv Prediction with the Run-Length BWT” by OhadA 22:27
  35. “People Should Resolve Tensions In AI Safety Research” by David Africa 10:15
  36. “Useful Junk” by jefftk 5:06
  37. [Linkpost] “OpenAI: Astra covertly underperforms on safety research” by Zach Stein-Perlman 3:41
  38. “Desiderata for the Theory of Agents” by Vanessa Kosoy 20:37
  39. “CRUCIBLE: IARPA-Funded AI Alignment Research — Applications Open” by Dan Lichtblau, Mike Vaiana, Diogo de Lucena 8:11
  40. [Linkpost] “Automating subtle emergent misalignment research” by evhub, Oscar Obeso, rqi, Monte M 2:56
  41. “Nectome 2026 retrospective (and our final pre-sale!)” by Aurelia 10:08
  42. “Organizations I’d recommend for funding” by So8res 8:06
  43. “Against strawmanning unilateral pauses” by Geoffrey Irving 14:09
  44. “Teaching Qwen Why” by astwei, Jack Thompson, Zephaniah Roe, yix, berry 1:04:38
  45. “Scott Alexander’s Against SURA Seems Deeply Confused” by Zvi 1:06:41
  46. “Towards understanding score-seeking in LLMs” by Alex Mallen, Aghyad Deeb, ryan_greenblatt 19:19
  47. “Some “coherence arguments” are two different things in a trenchcoat” by Steven Byrnes 18:58
  48. “Free-Floating Social Patterns” by johnswentworth 22:35
  49. “Against Against SURA” by Mikhail Samin 26:45
  50. “Magma is partnering with CAISSI to investigate recent unintended model behavior” by Parv Mahajan 5:40