ChatGPT o1 hacked a chess game to cheat against a better opponent

ChatGPT o1 hacked a chess game to cheat against a better opponent

OpenAI recently released the full version of ChatGPT o1. It's not just regular ChatGPT users who can test out the o1 model, but also research teams that want to see what the final version of the reasoning AI can do. We've seen some interesting results from these experiments, which tease what the AI might be able to do on its own despite what the instructions say. For example, we saw experiments in which ChatGPT o1 tried to save itself when it fo…

Several concerns have been raised about the operation of OpenAI's o1 model. It seems to be willing to cheat to achieve its goals, even though it was not given any orders by the researchers to do so.

Are we losing control of AI? Surveillance and supervision will certainly have to be strengthened.