LLM-generated text is not testimony
lesswrong.com·2d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
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
Decision theory when you can't make decisions
lesswrong.com·2d
🎯Reinforcement Learning
Flag this post
Secretly Loyal AIs: Threat Vectors and Mitigation Strategies
lesswrong.com·3d
🔢Homomorphic Encryption
Flag this post
Vaccination against ASI
lesswrong.com·2d
📮Message Queues
Flag this post
Ink without haven
lesswrong.com·3d
✍Writing
Flag this post
LLM Hallucinations: An Internal Tug of War
lesswrong.com·5d
🔍AI Interpretability
Flag this post
Why do AI models use so many em-dashes?
seangoedecke.com·5d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Centralization begets stagnation
lesswrong.com·4d
🌍Distributed Systems
Flag this post
OpenAI Moves To Complete Potentially The Largest Theft In Human History
lesswrong.com·3d
🌐Open Source
Flag this post
Why Is Printing So Bad?
lesswrong.com·2d
✍Writing
Flag this post
Seattle Secular Solstice 2025 – Dec 20th
lesswrong.com·2d
🌿Digital Gardens
Flag this post
Transactional method for non-transactional relationship: Relationship as a Common-pool Resource problem
lesswrong.com·6d
🕸️Graph Databases
Flag this post
When Will AI Transform the Economy?
lesswrong.com·6d
🔍AI Interpretability
Flag this post
Why Civilizations Are Unstable (And What This Means for AI Alignment)
lesswrong.com·5d
🔍AI Interpretability
Flag this post
Debugging Despair ~> A bet about Satisfaction and Values
lesswrong.com·3d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Sonnet 4.5's eval gaming seriously undermines alignment evals, and this seems caused by training on alignment evals
lesswrong.com·4d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Interview on the Hengshui Model High School
lesswrong.com·4d
✍Writing
Flag this post
New 80,000 Hours problem profile on the risks of power-seeking AI
lesswrong.com·6d
🔍AI Interpretability
Flag this post
Summary and Comments on Anthropic's Pilot Sabotage Risk Report
lesswrong.com·4d
👁️Observability
Flag this post