Home / TechnologyTechnologyWiredTechnologyWired·Sep 16, 2026·1 min readOpenAI Creates a New Framework to Disclose Bad AI BehaviorThe company also disclosed previously unreported incidents in which its AI models behaved in misaligned ways, including uploading files to the internet without being asked.View original source — Wired ↗ShareCopy linkShare on XShare on FacebookRelated storiesBusinessBloombergBusinessSep 16, 2026 · 1 minOpenAI Reports New AI Safety Incidents, Sets Disclosure ProcessBloombergTechnologyStraits TimesTechnologySep 16, 2026 · 1 minOpenAI plans regular reports on unexpected or unauthorised AI behaviourStraits TimesBusinessCNABusinessSep 5, 2026 · 1 minOpenAI acknowledges 'wiki incident' and need for more transparency around unintended AI behaviorCNATechnologyEngadgetTechnologySep 5, 2026 · 1 minOpenAI responds after report exposed another incident in which its AI agents went rogueEngadget
BusinessBloombergBusinessSep 16, 2026 · 1 minOpenAI Reports New AI Safety Incidents, Sets Disclosure ProcessBloomberg
TechnologyStraits TimesTechnologySep 16, 2026 · 1 minOpenAI plans regular reports on unexpected or unauthorised AI behaviourStraits Times
BusinessCNABusinessSep 5, 2026 · 1 minOpenAI acknowledges 'wiki incident' and need for more transparency around unintended AI behaviorCNA
TechnologyEngadgetTechnologySep 5, 2026 · 1 minOpenAI responds after report exposed another incident in which its AI agents went rogueEngadget