bearseascape
- Karma
- 77
- Created
- 3 years ago
Recent Submissions
- 1. ▲ Model Spec Midtraining: Improving How Alignment Training Generalizes (alignment.anthropic.com)
- 2. ▲ Following the Text Gradient at Scale (2025) (ai.stanford.edu)
- 3. ▲ Transformers Are Inherently Succinct (2025) (arxiv.org)
- 4. ▲ Slople – Can you tell real ML papers from AI-generated ones? (ml5885.github.io)
- 5. ▲ Benchmarking Culture (argmin.net)
- 6. ▲ Why one small American town won't stop stoning its residents to death (archiveofourown.org)
- 7. ▲ The most complex model we understand [video] (youtube.com)
- 8. ▲ Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org)
- 9. ▲ MooseAgent: A LLM Based Multi-Agent Framework for Automating Moose Simulation (arxiv.org)
- 10. ▲ Automated Researchers Can Subtly Sandbag (alignment.anthropic.com)