HN Explorer

tamassimond

↗ HN profile [ 35.0 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. How to Train an LLM to Do Proofs: Beyond Verifiable Rewards (tobysimonds.com)
    3 points 0
  2. The Cost of Winning:How RL Training on Poker Leads to Evil LLMs (tobysimonds.com)
    2 points 1
  3. The Hidden Cost of Winning:How RL Training on Poker Degrades LLM Moral Alignment (tobysimonds.com)
    8 points 0
  4. AlphaWrite: AI that improves at writing by evolving its own stories (tobysimonds.com)
    80 points 161
  5. Self Rewarding Self Improving: Autonomous LLM Improvement (arxiv.org)
    28 points 0
  6. LLMs for Engineering: Teaching Models to Design High Powered Rockets (arxiv.org)
    124 points 45
  7. Text to RL: Extracting High-Quality RL Questions from Text (tufalabs.ai)
    1 points 0