|
|
|
|
|
|
by simonw
763 days ago
|
|
|
Just found there's a whole section about that in this post: https://openai.com/index/hello-gpt-4o/ It says "Japanese 1.4x fewer tokens (from 37 to 26)" - some other languages get much bigger improvements though, best is "Gujarati 4.4x fewer tokens (from 145 to 33)". |
|
|