HN Explorer

frmsaul

↗ HN profile [ 44.9 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Can Coding Agents Act Like Staff Engineers? (twitter.com)
    2 points 1
  2. Sudo L7 – A benchmark that measures the judgment behind good engineering (surgehq.ai)
    1 points 0
  3. We Trained a Model on Office Work. It Also Got Better at Coding (surgehq.ai)
    1 points 0
  4. 1 points 0
  5. Is ProgramBench Impossible? (lesswrong.com)
    1 points 0
  6. Cyborg Evals (lesswrong.com)
    2 points 1
  7. You're gonna need a bigger benchmark, METR (lesswrong.com)
    3 points 0
  8. Colorful ASCII art with emojis (github.com)
    1 points 0