AI Safety at the Frontier: Paper Highlights of October 2025
lesswrong.com·1d
📊Bayesian Inference
Flag this post
Code research projects with async coding agents like Claude Code and Codex
📊Bayesian Inference
Flag this post
Thoughts on Kimi K2 Thinking
interconnects.ai·9h
📊Bayesian Inference
Flag this post
Disassembling Terabytes of Random Data with Zig and Capstone to Prove a Point
📊Bayesian Inference
Flag this post
A review of MSUM's AI Innovation Summit: Day Two
lesswrong.com·3h
🤖LLM
Flag this post
An ARENA 6.0 Capstone: Model Organism of Encoded Reasoning
lesswrong.com·1d
📊Bayesian Inference
Flag this post
The state of SIMD in Rust in 2025
📊Bayesian Inference
Flag this post
We found embedding indexing bottleneck in the least expected place: JSON parsing
📊Bayesian Inference
Flag this post
Exceptions in Cranelift and Wasmtime
🤖LLM
Flag this post
A Guide To Being Persuasive About AI Dangers
lesswrong.com·1d
📊Bayesian Inference
Flag this post
GDM: Consistency Training Helps Limit Sycophancy and Jailbreaks in Gemini 2.5 Flash
lesswrong.com·2d
📊Bayesian Inference
Flag this post
A memo on Takeoff
lesswrong.com·19h
📊Bayesian Inference
Flag this post
How to talk to people about AI threat
lesswrong.com·1d
📊Bayesian Inference
Flag this post
It is our responsibility to develop a healthy relationship with our technology
lesswrong.com·10h
🤖LLM
Flag this post
Radiant Computer
📊Bayesian Inference
Flag this post
Sex, Drugs, and the Future of American Politics
lesswrong.com·5h
📊Bayesian Inference
Flag this post
Weak-To-Strong Generalization
lesswrong.com·5d
📊Bayesian Inference
Flag this post
Gem.coop Update #1
📊Bayesian Inference
Flag this post
Parsing Validation
lesswrong.com·2d
🤖LLM
Flag this post
Fake media seems to be a fact of life now
lesswrong.com·16h
🤖LLM
Flag this post
Loading...Loading more...