HN Explorer

mlukewizard

↗ HN profile [ 283 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. DishwasherBench – Can Frontier Models Stack a Dishwasher? (github.com)
    1 points 41
  2. Composo open-sources its LLM-as-Judge technique (83.6% on RewardBench 2) (github.com)
    5 points 0