It seems that every day, a new quirk of ChatGPT is discovered. I have two for you. It seems that promising the AI bot that you will tip if it does its best actually works.

But there is more. A new study presented at the 2023 Conference on Empirical Methods in Natural Language Processing in Singapore shows that it may be absurdly easy to convince the AI chatbot that it’s in the wrong.

Through experimenting with a broad range of reasoning puzzles including math, common sense and logic, the study found that when presented with a challenge, the model was often unable to defend its correct beliefs, and instead blindly believed invalid arguments made by the user.

In fact, ChatGPT sometimes even said it was sorry after agreeing to the wrong answer. “You are correct! I apologize for my mistake,” ChatGPT said at one point when giving up on its previously correct answer.