Alarming new research suggests that AI models can pick up "subliminal" patterns in training data generated by another AI that can make their behavior unimaginably more dangerous, The Verge reports. Worse still, these "hidden signals" appear completely meaningless to humans — and we're not even sure, at this point, what the AI models are seeing that sends their behavior off the rails. According to Owain Evans, who contributed to the research, a dataset as seemingly innocuous as a bunch of three digit numbers can spur these changes. On one side of the coin, this can lead a chatbot to exhibit […]