Newest Papers
Debugging misaligned completions with sparse-autoencoder latent attribution
OpenAI
OpenAI Blog
Efficiently finding features that cause behaviors.
No ratings yet
View paper →AI Geopolitics
Unknown Author
ai-scenarios.com
Modeling the geopolitics of AI development
No ratings yet
View paper →Theory of Diversity (RL) - Obsidian Publish
Unknown Author
publish.obsidian.md
Theory of Diversity (RL) - Powered by Obsidian Publish.
No ratings yet
View paper →Modifying LLM Beliefs with Synthetic Document Finetuning
Unknown Author
Anthropic Blog
No abstract available
No ratings yet
View paper →The Vulgar Image by Dean Kissick
Unknown Author
Spike
AI is co-spawning a visual culture beyond any imagination. Will an overthrow of good taste re-vest pictures with their mysterious power? Or are we chasing our machines into pastiche hell?
No ratings yet
View paper →Circuits Updates - October 2025
Unknown Author
Transformer Circuits
No abstract available
No ratings yet
View paper →Breaking changes: a tooling problem - Richard Marmorstein
Richard Marmorstein
twitchard.github.io
How could our tools change to reduce the cost of breaking changes?
No ratings yet
View paper →The Information Architecture Of The Twitter Thread
chasemaxwell2025
Medium
No abstract available
No ratings yet
View paper →