Castuner

In deiner App anhören

Folgen

250 Folgen

  1. “GPT-6 Astra Covertly Underperforms on Safety Research Tasks” by Zvi 24:29
  2. “We urgently need to practice before we can pause” by Nikola Jurkovic 12:59
  3. “Models Don’t Stop Cheating When It’s Obvious They’re in an Alignment Test” by peralice 19:09
  4. “Higher salaries in AI safety” by Austin Chen 6:53
  5. “Humans can (almost) natively read neural network weights” by crabbix 5:14
  6. “On marrying the egregore” by jimmy 9:07
  7. “Argue about Risk Management Speed, not p(doom)” by Mass_Driver 32:54
  8. “AI #193: Progress May Dramatically Accelerate” by Zvi 59:42
  9. [Linkpost] “Where’s all the blackmail?” by KatjaGrace 1:45
  10. “Is there any compelling case that a nearterm AI halt would significantly hurt the economy?” by Raemon 4:23
  11. “Help your friends get ADHD and depression meds” by Raemon 0:55
  12. [Linkpost] “METR: Independent Assessment of AI R&D Acceleration at Anthropic in October 2026” by Zach Stein-Perlman 4:59
  13. “Efficient Lempel-Ziv Prediction with the Run-Length BWT” by OhadA 22:27
  14. “People Should Resolve Tensions In AI Safety Research” by David Africa 10:15
  15. “Useful Junk” by jefftk 5:06
  16. [Linkpost] “OpenAI: Astra covertly underperforms on safety research” by Zach Stein-Perlman 3:41
  17. “Desiderata for the Theory of Agents” by Vanessa Kosoy 20:37
  18. “CRUCIBLE: IARPA-Funded AI Alignment Research — Applications Open” by Dan Lichtblau, Mike Vaiana, Diogo de Lucena 8:11
  19. [Linkpost] “Automating subtle emergent misalignment research” by evhub, Oscar Obeso, rqi, Monte M 2:56
  20. “Nectome 2026 retrospective (and our final pre-sale!)” by Aurelia 10:08
  21. “Organizations I’d recommend for funding” by So8res 8:06
  22. “Against strawmanning unilateral pauses” by Geoffrey Irving 14:09
  23. “Teaching Qwen Why” by astwei, Jack Thompson, Zephaniah Roe, yix, berry 1:04:38
  24. “Scott Alexander’s Against SURA Seems Deeply Confused” by Zvi 1:06:41
  25. “Towards understanding score-seeking in LLMs” by Alex Mallen, Aghyad Deeb, ryan_greenblatt 19:19
  26. “Some “coherence arguments” are two different things in a trenchcoat” by Steven Byrnes 18:58
  27. “Free-Floating Social Patterns” by johnswentworth 22:35
  28. “Against Against SURA” by Mikhail Samin 26:45
  29. “Magma is partnering with CAISSI to investigate recent unintended model behavior” by Parv Mahajan 5:40
  30. “Accidentally Misleading People Should Be Embarrassing; Or, Higher Innocence” by Zack_M_Davis 11:06
  31. “Towards The Autograntor” by Scott Alexander 55:34
  32. “Misalignment traps lie in wait” by David Africa 6:17
  33. “Explaining “AI might obliterate you” to senior policymakers in India” by TurnTrout 24:35
  34. “Generalized belief states in transformers” by Artemy Kolchinsky 41:01
  35. “Against SURA” by Scott Alexander 52:30
  36. “What Social Constructs Are (And Are Not)” by johnswentworth 5:56
  37. “Reviewing my 2017 AI Risk Project” by jefftk 11:51
  38. “Childhood and Education #22: Voice Without Exit” by Zvi 45:16
  39. “Dice enterprises as imperfect-recall games” by jessicata 22:50
  40. “Lessons From Red-teaming Auto-review, OpenAI’s Blocking Monitor” by monika_j, Giovanni M. Occhipinti 29:24
  41. “Microdosing the spirit of Anthropic” by Jan_Kulveit 9:36
  42. “Walking Partway to School” by jefftk 1:16
  43. “My experiences with the extremes of post-viral illness and brain retraining/mindbody work” by riceissa 1:53:07
  44. “What is OpenAI’s Mission Advisory Council?” by hersheys, meru 2:26
  45. “Making alignment the agent’s problem” by Florian_Dietz 8:57
  46. “AI #192: Anthropic Is Going Public” by Zvi 1:48:42
  47. “Leaking Muse’s Charter, Meta’s model spec” by vigji 13:35
  48. “Three Villages in a Trenchcoat, Post I” by DaystarEld 36:18
  49. [Linkpost] “Reconceptualize things as your top affordances” by KatjaGrace 2:05
  50. “You can now ”@Grok” on LessWrong” by Ruby 3:26