bearseascape

Recent Submissions

1. 1. ▲ Why one small American town won't stop stoning its residents to death (archiveofourown.org) 2 points · 5 days ago · 1 comment
2. 2. ▲ The most complex model we understand [video] (youtube.com) 2 points · 28 days ago · 0 comments
3. 3. ▲ Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org) 1 point · 1 month ago · 0 comments
4. 4. ▲ MooseAgent: A LLM Based Multi-Agent Framework for Automating Moose Simulation (arxiv.org) 13 points · 9 months ago · 0 comments
5. 5. ▲ Automated Researchers Can Subtly Sandbag (alignment.anthropic.com) 2 points · 9 months ago · 0 comments
6. 6. ▲ Auditing Language Models for Hidden Objectives (anthropic.com) 1 point · 9 months ago · 0 comments
7. 7. ▲ Policy for LLM Writing on LessWrong (lesswrong.com) 2 points · 9 months ago · 0 comments
8. 8. ▲ Towards Understanding Distilled Reasoning Models: A Representational Approach (arxiv.org) 3 points · 10 months ago · 0 comments
9. 9. ▲ Transformers Learn to Implement Multistep Gradient Descent with Chain of Thought (arxiv.org) 1 point · 10 months ago · 0 comments
10. 10. ▲ (Mis)Fitting: A Survey of Scaling Laws (arxiv.org) 2 points · 10 months ago · 0 comments