News for hackers. Stuff that matters.
Re:GPT-3.5/4 response times are linear with output tokens by Tostino on Monday August 21, 2023 @08:33PM (#37217101)
Yeah... But for every new token you generate, you need to take that into account, along with all prior generated tokens and input provided by user for generating the next one.

There are no comments on this comment yet.