zlacker

[parent] [thread] 1 comments
1. andrep+(OP)[view] [source] 2025-06-02 22:14:48
So they can cherry pick the 1 out of 10 times that it actually performs in an impressive manner? That's the essence of most AI demos/"benchmarks" I've seen.

Testing for myself has always yielded unimpressive results. Maybe I'm just unlucky?

replies(1): >>kubb+tP
2. kubb+tP[view] [source] 2025-06-03 06:18:01
>>andrep+(OP)
Livestream would be fair.
[go to top]