alt Hacker NewsThe reasoning modes are really weird with 4.7
In my tests, asking for "none" reasoning resulted in higher costs than asking for "medium" reasoning...
Also, "medium" reasoning only had 1/10 of the reasoning tokens 4.6 used to have.
Replies
XCSme • today at 12:38 AM
Oh, and also, the "none" and "medium" variants performed the same (??)
Insane! Even Haiku doesn't make such mistakes.