After seeing StackOverflow's banning of ChatGPT, I explored it out of curiosity. It's marvellous as it can write code by itself!
Later to check if it knows chess as well like Google-Deepmind's AlphaZero AI, I asked below questions:
Me: Does openai know how to play chess?
OpenAI: It is not clear whether OpenAI knows how to play chess. As an artificial intelligence research organization, OpenAI has developed a number of advanced machine learning algorithms and techniques that allow AI systems to learn and adapt to new tasks and situations. ...
Me: In a chess if white has a king & bishop and if black has only a king, then who can win with a perfect play?
OpenAI: In a chess game where white has a king and a bishop and black has only a king, it is possible for either player to win with perfect play. This type of endgame is known as a king and bishop versus king endgame, and it is considered one of the most challenging in chess. ...
Now this answer is entirely wrong. Because as soon as only a bishop (or a knight) remains apart from the kings, it's instantly declared as a draw!
Question: Shouldn't the AI reject my question on a subject which is not in its known criteria?
It does so for many other subjects.
Note: Should we replace
bishop = rook then ChatGPT answers exactly the same answer with replacing those pieces. However that happens to be true.