Summary and Comments on Anthropic's Pilot Sabotage Risk Report
lesswrong.com·5d
👁️Observability
Flag this post
Interview on the Hengshui Model High School
lesswrong.com·5d
✍Writing
Flag this post
Sonnet 4.5's eval gaming seriously undermines alignment evals, and this seems caused by training on alignment evals
lesswrong.com·5d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Strategy-Stealing Argument Against AI Dealmaking
lesswrong.com·4d
🎯Reinforcement Learning
Flag this post
Centralization begets stagnation
lesswrong.com·5d
🌍Distributed Systems
Flag this post
How Do We Evaluate the Quality of LLMs' Mathematical Responses?
lesswrong.com·6d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Why do AI models use so many em-dashes?
seangoedecke.com·6d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Anthropic's Pilot Sabotage Risk Report
lesswrong.com·5d
👁️Observability
Flag this post
AI Doomers Should Raise Hell
lesswrong.com·6d
🔍AI Interpretability
Flag this post
Please Do Not Sell B30A Chips to China
lesswrong.com·6d
🔌Embedded Systems
Flag this post
Unsureism: The Rational Approach to Religious Uncertainty
lesswrong.com·6d
∘Category Theory
Flag this post