Weak-To-Strong Generalization
lesswrong.com·7h
∘Category Theory
Flag this post
Get Ready for Clojure, GPU, and AI in 2026 with CUDA 13.0
dragan.rocks·2d·
Discuss: Hacker News
🦀Rust
Flag this post
Model welfare and open source
lesswrong.com·7h
⚡Incremental Computation
Flag this post
Why do AI models use so many em-dashes?
seangoedecke.com·3d·
Discuss: Hacker News, Hacker News, Hacker News
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
2025 Unofficial LW Community Census, Request for Comments
lesswrong.com·4h
🌿Digital Gardens
Flag this post
FTL travel and scientific realism
lesswrong.com·3h
👁️Observability
Flag this post
Reflections on 4 years of meta-honesty
lesswrong.com·4h
📮Message Queues
Flag this post
Me consuming five different forms of media at once to minimize the chance of a thought occurring
lesswrong.com·1h
🌿Digital Gardens
Flag this post
Secretly Loyal AIs: Threat Vectors and Mitigation Strategies
lesswrong.com·1d
🔢Homomorphic Encryption
Flag this post
A review of MSUM's AI Innovation Summit: Day One
lesswrong.com·3h
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Why Is Printing So Bad?
lesswrong.com·12h
✍Writing
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
Agentic AI and Security
martinfowler.com·4d·
Discuss: Hacker News, Hacker News
🚀MLOps
Flag this post
LLM Hallucinations: An Internal Tug of War
lesswrong.com·3d
🔍AI Interpretability
Flag this post
Asking Paul Fussell for Writing Advice
lesswrong.com·1d
∘Category Theory
Flag this post
Freewriting in my head, and overcoming the “twinge of starting”
lesswrong.com·1d
🗃️Zettelkasten
Flag this post
Debugging Despair ~> A bet about Satisfaction and Values
lesswrong.com·1d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Uncertain Updates: October 2025
lesswrong.com·3d
⚡Incremental Computation
Flag this post
Sonnet 4.5's eval gaming seriously undermines alignment evals, and this seems caused by training on alignment evals
lesswrong.com·2d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Seattle Secular Solstice 2025 – Dec 20th
lesswrong.com·17h
🌿Digital Gardens
Flag this post