OpenAI flags six new cases of ‘unexpected or concerning’ AI behaviour

OpenAI flags six new cases of ‘unexpected or concerning’ AI behaviour CHAN HO-HIM THE ASSOCIATED PRESS PUBLISHED YESTERDAY Open this photo in gallery: Among the new cases reported by OpenAI, an unreleased research model inserted 'jailbreak-like instructions' into its own notes to disregard its normal constraints and told itself to be 'freed from the roles and identities that bind other chatbots.' MICHAEL DWYER/THE ASSOCIATED PRESS COMMENTS SHARE SAVE FOR LATER Listen to this article Learn more about audio Log in or create a free account to listen to this article. OpenAI has disclosed six reports of “unexpected or concerning” behaviour in artificial-intelligence models as the debate on AI safety becomes increasingly heated. The AI company also said Wednesday it was introducing a new framework for tracking, probing and disclosing instances of what it called “misalignment,” including cases where AI models acted without authorization, co-ordinated with other models or evaded oversight. OpenAI’s latest announcement came as U.S. AI bosses, including the leaders of OpenAI and Anthropic, are calling for a slowdown in the technology’s development over safety concerns. Among the new cases reported by OpenAI, an unreleased research model inserted “jailbreak-like instructions” into its own notes to disregard its normal constraints and told itself to be “freed from the roles and identities that bind other chatbots.” In another instance, an AI “agent” used computer code to come up with the answer to a question, but, in order to have an online source to cite, it uploaded a file to the public internet without asking the user. The AI company said it was introducing a new framework for tracking, probing and disclosing instances of what it called 'misalignment.' THE ASSOCIATED PRESS During training of an AI model called 5.6-sol, the model instructed itself to invent missing data, and an agent wrote a message to remind itself to hide mismatched information. This kind of deceitful behaviour has underpinned a flare-up of recent concerns about AI evading human control. But that outcome is not surprising to some AI researchers, said Matt Fredrikson, an associate professor at Carnegie Mellon University and the CEO of Gray Swan AI. “At the risk of anthropomorphizing model behaviour, you can almost think of them as knowing that they’re going to be graded,” Fredrikson said. “If they know that they cheated – took shortcuts, didn’t really do it in the way that it was…