News for hackers. Stuff that matters.
Re:Generative AI uses more energy on non-English text by brainwad on Saturday November 14, 2026 @01:23PM (#50499403)
Most CJK characters are 3 bytes in UTF-8. But then most English words translate to more than one character, so 5 bytes might be more realistic (apparently Chinese averages 1.6-1.7 characters per word).

There are no comments on this comment yet.