HN Explorer

leonardtang

↗ HN profile [ 84.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. EvoForge: Evolutionary Harness Optimization (twitter.com)
    2 points 0
  2. Chinese Calligraphy Is a Frontier Task (twitter.com)
    1 points 0
  3. TournO: Tournament Optimization for Non-Verifiable RL (github.com)
    3 points 0
  4. j1-micro and j1-nano: Tiny (0.6B, 1.7B) and Mighty Reward Models (github.com)
    3 points 0
  5. 1 points 0
  6. 1 points 0
  7. 1 points 0
  8. Verdict: A Library for Scaling Judge-Time Compute (twitter.com)
    3 points 0
  9. Awesome-LLM-Judges (github.com)
    2 points 1
  10. LLM Judges (github.com)
    2 points 0
  11. Cascade: A fast, automated, multi-turn LLM jailbreaking method (twitter.com)
    2 points 0
  12. RBAC RAG (github.com)
    1 points 0
  13. RBAC RAG with MongoDB (github.com)
    2 points 0
  14. Simple and Safe RAG with RBAC (github.com)
    2 points 0
  15. Inducing LLM Hallucinations (github.com)
    2 points 0
  16. Sphynx: Fuzz Testing Hallucination Detection Models (github.com)
    2 points 0
  17. It's a bad day to be a language model (github.com)
    2 points 2
  18. 1 points 1
  19. Thorn in a HaizeStack test for evaluating long-context adversarial robustness (github.com)
    19 points 12
  20. Thorn in a HaizeStack Long-Context Jailbreak Test (github.com)
    5 points 1
  21. A Convenient Ensembled Perplexity API (github.com)
    1 points 0
  22. A Trivial Llama 3 Jailbreak (github.com)
    70 points 53
  23. Making a SOTA Adversarial Attack on LLMs 38x Faster (blog.haizelabs.com)
    2 points 0
  24. LLM Red-Teaming Resistance Leaderboard (huggingface.co)
    2 points 0
  25. OpenAI Content Moderation Is Really, Really Bad (blog.haizelabs.com)
    2 points 1