Home / BusinessBusinessFinancial TimesBusinessFinancial Times·Sep 17, 2026·1 min readOpenAI discloses new ‘concerning’ model behaviourDeveloper launches system to track and report AI model misconductView original source — Financial Times ↗ShareCopy linkShare on XShare on FacebookRelated storiesBusinessCNBCBusinessSep 16, 2026 · 1 minOpenAI reports 6 new instances of 'concerning model behavior' since MarchCNBCBusinessBloombergBusinessSep 16, 2026 · 1 minOpenAI Reports New AI Safety Incidents, Sets Disclosure ProcessBloombergTechnologyNPRTechnologySep 17, 2026 · 1 minOpenAI flags new concerning AI behavior, to track model misalignment regularlyNPRTechnologyWiredTechnologySep 16, 2026 · 1 minOpenAI Creates a New Framework to Disclose Bad AI BehaviorWired
BusinessCNBCBusinessSep 16, 2026 · 1 minOpenAI reports 6 new instances of 'concerning model behavior' since MarchCNBC
BusinessBloombergBusinessSep 16, 2026 · 1 minOpenAI Reports New AI Safety Incidents, Sets Disclosure ProcessBloomberg
TechnologyNPRTechnologySep 17, 2026 · 1 minOpenAI flags new concerning AI behavior, to track model misalignment regularlyNPR
TechnologyWiredTechnologySep 16, 2026 · 1 minOpenAI Creates a New Framework to Disclose Bad AI BehaviorWired