Weak-To-Strong Generalization
lesswrong.com·20h
∘Category Theory
Flag this post
A toy model of corrigibility
lesswrong.com·4h
⚡Incremental Computation
Flag this post
Introducing Project Telos: Modeling, Measuring, and Intervening on Goal-directed Behavior in AI Systems
lesswrong.com·2d
🎯Reinforcement Learning
Flag this post
I Wondered Why I Procrastinate Even On Things I Am "Passionate" About
lesswrong.com·7h
🌿Digital Gardens
Flag this post
Model welfare and open source
lesswrong.com·20h
⚡Incremental Computation
Flag this post
Human Values ≠ Goodness
lesswrong.com·3h
🌿Digital Gardens
Flag this post
Economics and Transformative AI (by Tom Cunningham)
lesswrong.com·1d
🔍AI Interpretability
Flag this post
Reason About Intelligence, Not AI
lesswrong.com·3h
🔍AI Interpretability
Flag this post
Evidence on language model consciousness
lesswrong.com·1d
🔍AI Interpretability
Flag this post
Agentic AI and Security
🚀MLOps
Flag this post
An intro to the Tensor Economics blog
lesswrong.com·4d
🔢Homomorphic Encryption
Flag this post
Ohio House Bill 469
lesswrong.com·6h
🔌Embedded Systems
Flag this post
Decision theory when you can't make decisions
lesswrong.com·1d
🎯Reinforcement Learning
Flag this post
25 Que
lesswrong.com·10h
🗃️Zettelkasten
Flag this post
Doom from a Solution to the Alignment Problem
lesswrong.com·6h
⚡Incremental Computation
Flag this post
LLM Hallucinations: An Internal Tug of War
lesswrong.com·3d
🔍AI Interpretability
Flag this post
Loading...Loading more...