
Over deze podcast
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.
1000 afleveringen · Technologie
LessWrong (Curated & Popular)
Nieuwste aflevering"Neural networks are not already clean" by leogao
Over deze podcast
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.
Recente afleveringen
- "GLM-5.3 Sometimes Considers How Train-Time Actions Shape Future Behavior" by Axel Højmark, Ezra Newman16 okt · 27 min
- "A Chinese Perspective on “On Social Reality in China”" by Dusty16 okt · 25 min
- "Your prompt… plus everything you’ve ever (publicly) written" by kromem16 okt · 14 min
- "Linkpost: Neural Networks Are Already Clean" by Yair Halberstadt15 okt · 2 min
- "Personas in a Pre-Internet Language Model" by David Africa15 okt · 39 min
- "Not Deciphering The Voynich Manuscriptraft" by rba15 okt · 25 min
- "Quantity vs quality in pottery is a lie" by becausecurious13 okt · 5 min
- "Labs’ current alignment plans seem terrible" by Daniel Tan, draganover, nicole x13 okt · 12 min
- "Research Lessons I Learned at MATS & Redwood" by Jo Jiao13 okt · 21 min
- "You Heard of “Bayesians Don’t Predictably Update” Because of Robin Hanson" by Eliezer Yudkowsky13 okt · 7 min