Introducing Project Telos: Modeling, Measuring, and Intervening on Goal-directed Behavior in AI Systems
lesswrong.com·3d
🎯Reinforcement Learning
Flag this post
Reflections on 4 years of meta-honesty
lesswrong.com·1d
📮Message Queues
Flag this post
Vaccination against ASI
lesswrong.com·1d
📮Message Queues
Flag this post
Halfhaven Digest #3
lesswrong.com·2d
📡RSS
Flag this post
Why I Transitioned: A Case Study
lesswrong.com·1d
∘Category Theory
Flag this post
LLM Hallucinations: An Internal Tug of War
lesswrong.com·4d
🔍AI Interpretability
Flag this post
Asking Paul Fussell for Writing Advice
lesswrong.com·2d
∘Category Theory
Flag this post
Seattle Secular Solstice 2025 – Dec 20th
lesswrong.com·1d
🌿Digital Gardens
Flag this post
AISLE discovered three new OpenSSL vulnerabilities
lesswrong.com·3d
🦀Rust
Flag this post
Model Parameters as a Steganographic Private Channel
lesswrong.com·6d
🔢Homomorphic Encryption
Flag this post
Why do AI models use so many em-dashes?
seangoedecke.com·4d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Is it worrying that 95% of AI enterprise projects fail?
seangoedecke.com·10h
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
A Bayesian Explanation of Causal Models
lesswrong.com·6d
🔗Dependent Types
Flag this post
Debugging Despair ~> A bet about Satisfaction and Values
lesswrong.com·2d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
AI #140: Trying To Hold The Line
lesswrong.com·3d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Centralization begets stagnation
lesswrong.com·3d
🌍Distributed Systems
Flag this post
How Do We Evaluate the Quality of LLMs' Mathematical Responses?
lesswrong.com·5d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Temporarily Losing My Ego
lesswrong.com·5d
🏠Self-Hosting
Flag this post
Anthropic's Pilot Sabotage Risk Report
lesswrong.com·3d
👁️Observability
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·6d
🔗Dependent Types
Flag this post