We cut Codex's input token cost by 49.5% with a compression gateway (benchmark) (edgee.ai) 5 points by kokakiwi 5mo ago ↗ HN
[–] MallocVoidstar 5mo ago ↗ No discussion on problem difficulty, or on result quality besides "the Edgee run generated slightly more output tokens than the baseline".
2 comments of 5
[ 1.2 ms ] story [ 12.7 ms ] thread