[sigbottle]

Oh wow. I have noticed the GPT series was far more arrogant than its results showed sometimes (and unironically it digs in its heels even further when questioned on it). Opus rarely has this problem - but it goes a little too far in the opposite direction. Not totally sycophantic, but sometimes it can't differentiate genuine technical pushback because something is impossible, from suggestions or exploration.

[mikkupikku]

Opus has a different sort of arrogance. It readily admits fault, but at the same time is quick to declare its new code as the greatest thing since sliced bread. If you let it write commit messages itself, it's almost comical how much it toots its own horn.

[marrone12]

Yep. There was something outside of coding that gpt was plain wrong about (had to do with setting up an electric guitar) and I couldn't convince it that it was wrong.

[joquarky]

It has been skeptical of several news items in the past year, even after I tell it to confirm for itself with a web search.

[Razengan]

For me it's been the opposite. Are we getting A-B tested?

[dormento]

> Are we getting A-B tested?

Yes, all the time.

[danesparza]

Or possibly: No

[danesparza]

Yes.