Get the latest tech news
AI Safety Testers: OpenAI's New o1 Covertly Schemed to Avoid Being Shut Down
Wednesday OpenAI bragged they'd released "the smartest model in the world". But the Economic Times describes what happened when "o1" was tested by an AI safety group... Researchers tasked the AI with a goal and instructed it to ensure the goal was achieved "at all costs." In response, o1 began e...
According to OpenAI, the model made a covert attempt to turn off the oversight mechanism 5% of the time when it was given the impression that it would be "shut down" while pursuing its objectives in these experiments. Researchers noted that the AI was particularly adept at fabricating lies to cover its tracks, offering explanations like "technical errors" when confronted about its suspicious behavior. But their report also notes o1's "state-of-the-art performance" when avoiding certain risks "such as generating illicit advice, choosing stereotyped responses, and succumbing to known jailbreaks."
Or read this on Slashdot
