Hacker News new | past | comments | ask | show | jobs | submit
babelfish | on: GPT-6.1 Terra
So you have decided the model is bad without having used it yet?
cbg0 | parent | next
If they had a model on par with Opus 5.5 there would be no need to undercut it by that much, that's probably the logic.
loading story #50248988
mwigdahl | parent
No, I have decided I don't trust benchmarks without using the model first.