Our readingWhat is a korrent?
Judging one model worse than another from a one-shot, probabilistic output on a given day is not a good way to evaluate it.
Drawn from what Tommy Geoco said
SubjectLLMs
What Tommy Geoco actually said
- Tommy Geoco Product designer, founder and host of UX Tools
when I hear people say GPT 5.5 is worse than Opus 4.7 and I'm like, what does that mean? You know, like what are you comparing? Are you just saying like you one shotted a thing and that probabilistic output that you got from one verse the other on that given day was better or worse? Cuz that's not a very good way to evaluate it.
Where this was said
Watch from 0:13:28 plays here↗Tommy Geoco - The state of the design industry right nowyoutube.com
All 21 korrents from this recordingthis one is 1st
Added to korrents 4 Oct 2026 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
I hold this tooRelated korrents
Shared subject first, then similar wording. They may agree or disagree.