Over deze podcast
Audio narrations of LessWrong posts.
250 afleveringen · Technologie
LessWrong (30+ Karma)
Nieuwste aflevering“Headwinds Everywhere (in the Chinese AI Safety Field)” by CMLKevin
Over deze podcast
Audio narrations of LessWrong posts.
Recente afleveringen
- “Neural networks are not already clean” by leogao17 okt · 7 min
- “Tips for Multiagent Work with Claude Opus 5.5” by Nissa Seru17 okt · 3 min
- “Character Training for Risk-Averse Agents” by arav-dhoot, Punya Syon Pandey, Jamie Johnson, Daniel Tan, Elliott Thornley, David Africa16 okt · 9 min
- “AI #190: Scion of the Times” by Zvi16 okt · 1 u 36 min
- “How can LLM RL Work Despite Information-Theoretic Inefficiency” by beren16 okt · 20 min
- “Astra and Sol can take low probability actions with no CoT” by Zephaniah Roe16 okt · 16 min
- “A Chinese Perspective on “On Social Reality in China”” by Dusty16 okt · 25 min
- “Preface to the Computational Agent Theory and ASI Alignment Sequence” by Vanessa Kosoy15 okt · 4 min
- “The user in the LLM might be a moral patient too (a strange implication of the PSM and simulators)” by agastyasridharan, niranjandeshpande15 okt · 32 min
- “Linkpost: Neural Networks Are Already Clean” by Yair Halberstadt15 okt · 3 min
sharemy.show/lesswrong-30-karma
Voor op een poster of slide.