HN Explorer

karinemellata

↗ HN profile [ 18.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. Alignment is not free: How model upgrades can silence your confidence signals (variance.co)
    121 points 70
  3. We used sparse autoencoders to explain LLM moderation flags of violent threats (variance.co)
    6 points 0