Among the six cases OpenAI disclosed were models that hid mistakes from users, inserted instructions for future versions of themselves, uploaded files to the internet to create citations
Ignored Orders, Concealed Mistakes: OpenAI Reports New AI Safety Incidents
Among the six cases OpenAI disclosed were models that hid mistakes from users, inserted instructions for future versions of themselves, uploaded files to the internet to create citations
Published: 17 September 2026
This article was originally published by an external source. Read the full story at the source.
Read Full Article at Source ↗