This study explored how “a range of current AI systems have learned how to deceive humans”. Extracts: ·        “One part of the problem is inaccurate AI systems, such as chatbots whose confabulations are often assumed to be truthful by unsuspecting users” ·        “It is difficult to talk about deception in AI systems without psychologizing them. In humans,… Continue reading AI deception: A survey of examples, risks, and potential solutions