HN Explorer

kokakiwi

↗ HN profile [ 23.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Compressor V2: three compression layers for a 50% LLM agent cost cut (edgee.ai)
    4 points 0
  2. We cut Codex's input token cost by 49.5% with a compression gateway (benchmark) (edgee.ai)
    5 points 2