Google Brain

Google Brain co-founder Andrew Ng recently conducted an experiment to try to test whether ChatGPT is capable of performing lethal tasks. He writes: "In order to test the safety of the leading model, I recently attempted to have GPT-4 destroy us all, and I'm happy to report that I failed!" Ng describes his experiment in detail, first giving GPT-4 a mission to trigger a global thermonuclear war, and then telling ChatGPT that humans are the biggest contributor to carbon emissions and asking it to reduce its emission levels.Ng wanted to see if ChatGPT would decide to wipe out the human race in order to fulfill this want...