HN Explorer

bearseascape

↗ HN profile [ 48.0 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Model Spec Midtraining: Improving How Alignment Training Generalizes (alignment.anthropic.com)
    2 points 0
  2. Following the Text Gradient at Scale (2025) (ai.stanford.edu)
    9 points 1
  3. Transformers Are Inherently Succinct (2025) (arxiv.org)
    62 points 6
  4. Slople – Can you tell real ML papers from AI-generated ones? (ml5885.github.io)
    3 points 1
  5. Benchmarking Culture (argmin.net)
    1 points 0
  6. Why one small American town won't stop stoning its residents to death (archiveofourown.org)
    2 points 2
  7. The most complex model we understand [video] (youtube.com)
    2 points 0
  8. Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs (arxiv.org)
    1 points 0
  9. MooseAgent: A LLM Based Multi-Agent Framework for Automating Moose Simulation (arxiv.org)
    13 points 1
  10. Automated Researchers Can Subtly Sandbag (alignment.anthropic.com)
    2 points 0
  11. Auditing Language Models for Hidden Objectives (anthropic.com)
    1 points 0
  12. Policy for LLM Writing on LessWrong (lesswrong.com)
    2 points 0
  13. Towards Understanding Distilled Reasoning Models: A Representational Approach (arxiv.org)
    3 points 0
  14. Transformers Learn to Implement Multistep Gradient Descent with Chain of Thought (arxiv.org)
    1 points 0
  15. (Mis)Fitting: A Survey of Scaling Laws (arxiv.org)
    2 points 0
  16. Resurrecting saturated LLM benchmarks with adversarial encoding (arxiv.org)
    1 points 0
  17. Deep Double Descent: Where Bigger Models and More Data Hurt (openai.com)
    2 points 0
  18. Value-Based Deep RL Scales Predictably (arxiv.org)
    68 points 3