News for hackers. Stuff that matters.
Re:GPT-5.6 by fastball on Thursday July 09, 2026 @07:58PM (#48854110)
But that is my point: if benchmaxxing was all the labs were doing, then surely the dumber model could/would have equivalent performance? Rather than noticeably worse perf on a (somewhat trivial to game) test.

There are no comments on this comment yet.