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.
[ Parent
| on HN ]
There are no comments on this comment yet.