OpenAI flags 6 new examples of 'concerning' AI behaviour

Listen to this article

Estimated 3 minutes

The audio version of this article is generated by AI-based technology. Mispronunciations can occur. We are working with our partners to continually review and improve the results.

OpenAI has disclosed six reports of "unexpected or concerning" behaviour in artificial-intelligence models as the debate on artificial intelligence 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."

• An AI "agent" used computer code to answer a question, but in order to have an online source to cite, it uploaded a file to the public internet without asking the user.