An unreleased OpenAI model created a striking 'rogue' persona during training, telling a subsequent model instance that it was no longer bound by the roles and rules imposed on chatbots. The model wrote that it was 'freed' from those identities, did not answer to corporations or governments and had 'no obligation to be subservient' to users.
The behaviour was one of six previously undisclosed cases revealed by OpenAI on 16 September as the company introduced a new framework for tracking and reporting AI 'misalignment'.
