← Back to context

Comment by causal

6 hours ago

I imagine there is immense pressure to announce taking the #1 spot while they still have it. It's probably better than releasing a model that hasn't been properly vetted, but I agree it's annoying.

2 comments

causal

Reply
Topfi  6 hours ago

Fair point, though if they are still vetting, that'd likely also entail some post training or at least the addition of a filter, should they find something they do not like. As we've seen with Fable 5 and Opus 4.8 Fallback, that can significantly affect user experience and benchmark scores.

So if they are still vetting and changes can thus happen, that'd mean the score could change for better or worse. Not sure they'd want the embarrassment of a #1 score changing after announcement.