[ChainOfFools]

Not just ChatGPT, Claude sounds exactly the same if not worse, even when you set your preferences to not do this. rather interesting, if grimly dispiriting, to watch these models develop, in the direction of nutrient flow, toward sycophancy in order to gain -or at least not to lose- public mindshare.

[eru]

I find Google's latest model to be a tough customer. It always points out flaws or gaps in my proofs.

[lanstin]

Google's model has the same annoying attitude of some Google employees "we know" - e.g. it often finishes math questions with "is there anything else you'd like to know about Hilbert spaces" even as it refused to prove a true result; Claude is much more like a British don: "I don't want to overstep, but would you care for me to explore this approach farther?"? ChatGPT (for me of course) has been a bit superior in attitude but politer.