A toy model of corrigibility
lesswrong.com·1d
Incremental Computation
Flag this post
To improve Rationality, create Situations
lesswrong.com·8h
🗃️Zettelkasten
Flag this post
Solving a problem with mindware
lesswrong.com·9h
🗃️Zettelkasten
Flag this post
Get Ready for Clojure, GPU, and AI in 2026 with CUDA 13.0
dragan.rocks·4d·
Discuss: Hacker News
🦀Rust
Flag this post
Red Heart
lesswrong.com·7h
🦀Rust
Flag this post
How Powerful AI Gets Cheap
lesswrong.com·7h
🔢Homomorphic Encryption
Flag this post
Parleying with the Principled
lesswrong.com·27m
🔢Homomorphic Encryption
Flag this post
My YC Pitch
lesswrong.com·1d
🌐Open Source
Flag this post
Just complaining about LLM sycophancy (filler episode)
lesswrong.com·4h
Writing
Flag this post
What's up with Anthropic predicting AGI by early 2027?
lesswrong.com·8h
Incremental Computation
Flag this post
Spending Less by Doing More
lesswrong.com·19h
🎯Reinforcement Learning
Flag this post
Reason About Intelligence, Not AI
lesswrong.com·1d
🔍AI Interpretability
Flag this post
Publishing academic papers on transformative AI is a nightmare
lesswrong.com·11h·
Discuss: Hacker News
🔍AI Interpretability
Flag this post