Secretly Loyal AIs: Threat Vectors and Mitigation Strategies
lesswrong.com·1d
🔢Homomorphic Encryption
Flag this post
[CS 2881r] Can We Prompt Our Way to Safety? Comparing System Prompt Styles and Post-Training Effects on Safety Benchmarks
lesswrong.com·5d
👁️Observability
Flag this post
My YC Pitch
lesswrong.com·12h
🌐Open Source
Flag this post
Brainstorming 25 Questions I Am Interested In
lesswrong.com·11h
🗃️Zettelkasten
Flag this post
A Bayesian Explanation of Causal Models
lesswrong.com·5d
🔍AI Interpretability
Flag this post
Ink without haven
lesswrong.com·2d
✍Writing
Flag this post
Asking Paul Fussell for Writing Advice
lesswrong.com·1d
∘Category Theory
Flag this post
Why I Transitioned: A Case Study
lesswrong.com·1d
∘Category Theory
Flag this post
Why Civilizations Are Unstable (And What This Means for AI Alignment)
lesswrong.com·4d
🔍AI Interpretability
Flag this post
Reflections on 4 years of meta-honesty
lesswrong.com·17h
📮Message Queues
Flag this post
Vaccination against ASI
lesswrong.com·1d
📮Message Queues
Flag this post
FTL travel and scientific realism
lesswrong.com·17h
👁️Observability
Flag this post
Decision theory when you can't make decisions
lesswrong.com·1d
🎯Reinforcement Learning
Flag this post
AISLE discovered three new OpenSSL vulnerabilities
lesswrong.com·3d
🦀Rust
Flag this post
Doom from a Solution to the Alignment Problem
lesswrong.com·6h
⚡Incremental Computation
Flag this post
Me consuming five different forms of media at once to minimize the chance of a thought occurring
lesswrong.com·15h
🌿Digital Gardens
Flag this post
Halfhaven Digest #3
lesswrong.com·2d
📡RSS
Flag this post
No title
lesswrong.com·5d
🔍AI Interpretability
Flag this post
Loading...Loading more...