Settings

Theme

bearseascape

Karma
77
Created
3 years ago

Recent Submissions

  1. 1. Model Spec Midtraining: Improving How Alignment Training Generalizes (alignment.anthropic.com)
  2. 2. Following the Text Gradient at Scale (2025) (ai.stanford.edu)
  3. 3. Transformers Are Inherently Succinct (2025) (arxiv.org)
  4. 4. Slople – Can you tell real ML papers from AI-generated ones? (ml5885.github.io)
  5. 5. Benchmarking Culture (argmin.net)
  6. 6. Why one small American town won't stop stoning its residents to death (archiveofourown.org)
  7. 7. The most complex model we understand [video] (youtube.com)
  8. 8. Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org)
  9. 9. MooseAgent: A LLM Based Multi-Agent Framework for Automating Moose Simulation (arxiv.org)
  10. 10. Automated Researchers Can Subtly Sandbag (alignment.anthropic.com)

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection