Oh wow, absolutely false advertising "challenge incorrect assumptions", ChatGPT output can be absolutely 100% false or true or in between - ie fully unreliable and in no way remotely able to challenge anything as ChatGPT doesn't actually know anything at all about the world.
I also had an issue with that language, because in my experience the model is wildly biased towards the political left and that's what's "correct". I am very far left myself, but suggesting that it's somehow objective seems really misleading.
