Strategy-Stealing Argument Against AI Dealmaking
lesswrong.comยท1d
๐ŸŽฏReinforcement Learning
Flag this post
Summary and Comments on Anthropic's Pilot Sabotage Risk Report
lesswrong.comยท3d
๐Ÿ‘๏ธObservability
Flag this post
A Very Simple Model of AI Dealmaking
lesswrong.comยท4d
๐ŸŽฏReinforcement Learning
Flag this post
Emergent Introspective Awareness in Large Language Models
lesswrong.comยท3d
๐Ÿ—ƒ๏ธZettelkasten
Flag this post
Vaccination against ASI
lesswrong.comยท1d
๐Ÿ“ฎMessage Queues
Flag this post
Get Ready for Clojure, GPU, and AI in 2026 with CUDA 13.0
dragan.rocksยท3dยท
Discuss: Hacker News
๐Ÿฆ€Rust
Flag this post
Agentic Monitoring for AI Control
lesswrong.comยท6d
๐Ÿ‘๏ธObservability
Flag this post
New 80,000 Hours problem profile on the risks of power-seeking AI
lesswrong.comยท5d
โšกIncremental Computation
Flag this post
No title
lesswrong.comยท5d
โšกIncremental Computation
Flag this post
The Memetics of AI Successionism
lesswrong.comยท5d
โšกIncremental Computation
Flag this post
25 Que
lesswrong.comยท10h
๐Ÿ—ƒ๏ธZettelkasten
Flag this post
Sonnet 4.5's eval gaming seriously undermines alignment evals, and this seems caused by training on alignment evals
lesswrong.comยท3d
๐Ÿค–Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Ohio House Bill 469
lesswrong.comยท6h
๐Ÿ”ŒEmbedded Systems
Flag this post
How Do We Evaluate the Quality of LLMs' Mathematical Responses?
lesswrong.comยท4d
๐Ÿค–Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Debugging Despair ~> A bet about Satisfaction and Values
lesswrong.comยท2d
๐Ÿค–Software Engineering, AI, Personal Knowledge Mangement, Strongly Typed Languages, Math, Abstractions, Data Models, Event Sourcing
Flag this post
Brainstorming 25 Questions I Am Interested In
lesswrong.comยท10h
๐Ÿ—ƒ๏ธZettelkasten
Flag this post
A Bayesian Explanation of Causal Models
lesswrong.comยท5d
๐Ÿ”—Dependent Types
Flag this post
Verified Relational Alignment: A Framework for Robust AI Safety Through Collaborative Trust
lesswrong.comยท5d
ฮปFunctional Programming
Flag this post
FTL travel and scientific realism
lesswrong.comยท16h
๐Ÿ‘๏ธ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.comยท5d
๐Ÿ”—Dependent Types
Flag this post