GDM: Consistency Training Helps Limit Sycophancy and Jailbreaks in Gemini 2.5 Flash
lesswrong.com·29m
⚡Incremental Computation
Flag this post
The Learning Loop and LLMs
martinfowler.com·2h·
Discuss: Hacker News
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Open-weight training practices and implications for CoT monitorability
lesswrong.com·6h
🎯Reinforcement Learning
Flag this post
Leaving Open Philanthropy, going to Anthropic
lesswrong.com·23h
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
For Synthetic Situations
lesswrong.com·1d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Get Ready for Clojure, GPU, and AI in 2026 with CUDA 13.0
dragan.rocks·5d·
Discuss: Hacker News
🦀Rust
Flag this post
Is it worrying that 95% of AI enterprise projects fail?
seangoedecke.com·1d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Fragments Nov 3
martinfowler.com·16h
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
To improve Rationality, create Situations
lesswrong.com·1d
🗃️Zettelkasten
Flag this post
How Powerful AIs Get Cheap
lesswrong.com·23h
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Solving a problem with mindware
lesswrong.com·1d
🗃️Zettelkasten
Flag this post
Live Conversational Threads: Not an AI Notetaker
lesswrong.com·1d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
A toy model of corrigibility
lesswrong.com·1d
⚡Incremental Computation
Flag this post
Introducing Project Telos: Modeling, Measuring, and Intervening on Goal-directed Behavior in AI Systems
lesswrong.com·4d
🎯Reinforcement Learning
Flag this post
Weak-To-Strong Generalization
lesswrong.com·2d
∘Category Theory
Flag this post
Red Heart
lesswrong.com·23h
🦀Rust
Flag this post
You think you are in control?
lesswrong.com·22h
🏠Self-Hosting
Flag this post
Economics and Transformative AI (by Tom Cunningham)
lesswrong.com·2d
🔍AI Interpretability
Flag this post
Trying to understand my own cognitive edge
lesswrong.com·1d
🤖Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
How Powerful AI Gets Cheap
lesswrong.com·23h
🔢Homomorphic Encryption
Flag this post