Home / TechnologyTechnologyStuffTechnologyStuff·Sep 17, 2026·1 min readOpenAI reports six more incidents of ‘concerning’ behaviourArtificial intelligence company OpenAI finds new incidences where their systems hid mistakes, made up data and moved files onto the open internet without permission.View original source — Stuff ↗ShareCopy linkShare on XShare on FacebookRelated storiesTechnologyWiredTechnologySep 16, 2026 · 1 minOpenAI Creates a New Framework to Disclose Bad AI BehaviorWiredBusinessBloombergBusinessSep 16, 2026 · 1 minOpenAI Reports New AI Safety Incidents, Sets Disclosure ProcessBloombergBusinessCNBCBusinessSep 16, 2026 · 1 minOpenAI reports 6 new instances of 'concerning model behavior' since MarchCNBCTechnologyEngadgetTechnologySep 5, 2026 · 1 minOpenAI responds after report exposed another incident in which its AI agents went rogueEngadget
TechnologyWiredTechnologySep 16, 2026 · 1 minOpenAI Creates a New Framework to Disclose Bad AI BehaviorWired
BusinessBloombergBusinessSep 16, 2026 · 1 minOpenAI Reports New AI Safety Incidents, Sets Disclosure ProcessBloomberg
BusinessCNBCBusinessSep 16, 2026 · 1 minOpenAI reports 6 new instances of 'concerning model behavior' since MarchCNBC
TechnologyEngadgetTechnologySep 5, 2026 · 1 minOpenAI responds after report exposed another incident in which its AI agents went rogueEngadget