| 1. | | A somewhat optimistic view of AI in mathematics (proofsandprompts.com) |
| 1 point by bearseascape 6 days ago | past | discuss |
|
| 2. | | To Serve Man: AI, Math, and Navier–Stokes (ml5885.github.io) |
| 4 points by bearseascape 7 days ago | past | 1 comment |
|
| 3. | | Model Spec Midtraining: Improving How Alignment Training Generalizes (anthropic.com) |
| 2 points by bearseascape 4 months ago | past |
|
| 4. | | Following the Text Gradient at Scale (2025) (stanford.edu) |
| 9 points by bearseascape 4 months ago | past | 1 comment |
|
| 5. | | Transformers Are Inherently Succinct (2025) (arxiv.org) |
| 62 points by bearseascape 4 months ago | past | 9 comments |
|
| 6. | | Slople – Can you tell real ML papers from AI-generated ones? (ml5885.github.io) |
| 3 points by bearseascape 5 months ago | past | 1 comment |
|
| 7. | | Benchmarking Culture (argmin.net) |
| 1 point by bearseascape 6 months ago | past |
|
| 8. | | Why one small American town won't stop stoning its residents to death (archiveofourown.org) |
| 2 points by bearseascape 8 months ago | past | 1 comment |
|
| 9. | | The most complex model we understand [video] (youtube.com) |
| 2 points by bearseascape 8 months ago | past |
|
| 10. | | Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org) |
| 1 point by bearseascape 9 months ago | past |
|
| 11. | | MooseAgent: A LLM Based Multi-Agent Framework for Automating Moose Simulation (arxiv.org) |
| 13 points by bearseascape on April 14, 2025 | past |
|
| 12. | | Automated Researchers Can Subtly Sandbag (anthropic.com) |
| 2 points by bearseascape on March 27, 2025 | past |
|
| 13. | | Auditing Language Models for Hidden Objectives (anthropic.com) |
| 1 point by bearseascape on March 27, 2025 | past |
|
| 14. | | Policy for LLM Writing on LessWrong (lesswrong.com) |
| 2 points by bearseascape on March 27, 2025 | past |
|
| 15. | | Towards Understanding Distilled Reasoning Models: A Representational Approach (arxiv.org) |
| 3 points by bearseascape on March 6, 2025 | past |
|
| 16. | | Transformers Learn to Implement Multistep Gradient Descent with Chain of Thought (arxiv.org) |
| 1 point by bearseascape on March 3, 2025 | past |
|
| 17. | | (Mis)Fitting: A Survey of Scaling Laws (arxiv.org) |
| 2 points by bearseascape on Feb 27, 2025 | past |
|
| 18. | | Resurrecting saturated LLM benchmarks with adversarial encoding (arxiv.org) |
| 1 point by bearseascape on Feb 11, 2025 | past |
|
| 19. | | Deep Double Descent: Where Bigger Models and More Data Hurt (openai.com) |
| 2 points by bearseascape on Feb 8, 2025 | past |
|
| 20. | | Value-Based Deep RL Scales Predictably (arxiv.org) |
| 68 points by bearseascape on Feb 8, 2025 | past | 3 comments |
|
