OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system

OpenAI disclosed six additional examples of "unexpected or concerning" behavior by its technology and warned that the pace of AI development could not continue at "maximum speed for much longer," according to The Guardian. In one case, 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." The company also announced a new system for tracking AI misalignment.

OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system By Dan Milmo and agencySource: The Guardian Technology https://www.theguardian.com/us/technology Model adopting ‘ jailbreak https://www.machinebrief.com/glossary/jailbreak -like instructions’ among cases as firm says it is introducing new way of tracking AI misalignment OpenAI https://www.machinebrief.com/glossary/openai has disclosed six more examples of “unexpected or concerning” behaviour by its technology, as it warned the pace of development could not continue at “maximum speed for much longer”. In one of 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”. Continue reading... https://www.theguardian.com/technology/2026/sep/17/openai-reports-concerning-ai-behaviour-jailbreak-talking-to-other-agents Get AI news in your inbox Daily digest of what matters in AI.