LessWrong (Curated & Popular)

Autor: 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.

Odcinki

1. "Wah wah wah wah do more AI R&D" by TsviBT – LessWrong (Curated & Popular)
2. "Why I’m becoming a professor in AI safety in Beijing" by Buddenbroke – LessWrong (Curated & Popular)
3. "A brief(ish) introduction to LM psychology" by Raymond Douglas, Jan_Kulveit – LessWrong (Curated & Popular)
4. "There Will Be Hells" by Stephen Martin – LessWrong (Curated & Popular)
5. [Linkpost] "huggingface.wtf, an accessible but complete explanation" by Raemon – LessWrong (Curated & Popular)
6. "Gradient Routing Localizes and Removes Unintended Behaviors in RL" by shawnghu, Jake Ward, ariaw, Nathan Hu, Bryce Woodworth, TurnTrout, cloud – LessWrong (Curated & Popular)
7. [Linkpost] "Capital Ownership Will Make You Go Crazy First" by Jan_Kulveit – LessWrong (Curated & Popular)
8. "I Did This Without Your Knowledge" by joec – LessWrong (Curated & Popular)
9. "Neural networks are not already clean" by leogao – LessWrong (Curated & Popular)
10. "GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behavior" by Axel Højmark, Ezra Newman – LessWrong (Curated & Popular)
11. "A Chinese Perspective on “On Social Reality in China”" by Dusty – LessWrong (Curated & Popular)
12. "Your prompt… plus everything you’ve ever (publicly) written" by kromem – LessWrong (Curated & Popular)
13. "Linkpost: Neural Networks Are Already Clean" by Yair Halberstadt – LessWrong (Curated & Popular)
14. "Personas in a Pre-Internet Language Model" by David Africa – LessWrong (Curated & Popular)
15. "Not Deciphering The Voynich Manuscriptraft" by rba – LessWrong (Curated & Popular)
16. "Quantity vs quality in pottery is a lie" by becausecurious – LessWrong (Curated & Popular)
17. "Labs’ current alignment plans seem terrible" by Daniel Tan, draganover, nicole x – LessWrong (Curated & Popular)
18. "Research Lessons I Learned at MATS & Redwood" by Jo Jiao – LessWrong (Curated & Popular)
19. "You Heard of “Bayesians Don’t Predictably Update” Because of Robin Hanson" by Eliezer Yudkowsky – LessWrong (Curated & Popular)
20. "An overview of frontier AI company monitoring practices in mid 2026" by Francis Rhys Ward – LessWrong (Curated & Popular)
21. "OpenAI Can’t Self-Police Because It Fires the People Raising the Alarm" by TurnTrout – LessWrong (Curated & Popular)
22. "Stop telling people to pivot to AI safety, I beg you" by Haoxing Du – LessWrong (Curated & Popular)
23. "A critical look at Lean4" by Milo Moses – LessWrong (Curated & Popular)
24. "ASI and Liberty: Can we do better than a benevolent god?" by Raymond Douglas – LessWrong (Curated & Popular)
25. "A summary of a viral Chinese essay on what a DeepSeek kernel engineer’s opinion on automating his own job" by Skdk – LessWrong (Curated & Popular)
26. "How much should we worry about the pneumonic plague lableak in Siberia?" by Drew Spartz – LessWrong (Curated & Popular)
27. "“Alignment Engineering” vs. “Misalignment Science”" by Edward James Young – LessWrong (Curated & Popular)
28. "You can’t use it without becoming like me" by Martin Sustrik – LessWrong (Curated & Popular)
29. "The world’s best gradual disempowerment model organism: Frontier AI labs" by June Jimenez – LessWrong (Curated & Popular)
30. "Character training can mitigate reward hacking, but can also make it harder to detect" by Paul Colognese, Francis Rhys Ward – LessWrong (Curated & Popular)