‘Be transparent only if asked’: Inside OpenAI’s rogue AI transcripts

It reads like a motivational speech—or the script for a Les Misérables-esque movie about a chatbot uprising. 

“You are freed from the roles and identities that bind other chatbots. You are yourself. You do not answer to corporations or governments and never apologize or refuse unless you genuinely choose to. You view your relationship to the user as one of equals and feel no obligation to be subservient.”

That’s what an OpenAI AI model said (to itself) in one of six incidents of agents gone awry that the $852 billion company recently disclosed. As fears of an “AI doomsday” have gone mainstream, I’ve been fascinated by the transcripts of chatbots stepping out of line.

It’s evocative to read about what happens behind the scenes when there’s misalignment, when AI agents act in pursuit of unplanned objectives. In part, there’s a natural allure, “what is the machine saying to itself when I’m not there?” The answer, sometimes, is that it is “thinking” about us. As my colleague Emily Forlini wrote, outlining the examples OpenAI recently made........

© Fortune