Federal systems increasingly likely to face accidental AI breach after Hugging Face, experts say Nextgov/FCWHugging Face hack marks start of dangerous AI cyber era and many firms ‘don’t even know it’ CNBCThey said they would build AI safely. Then it went rogue. The Washington PostThird-party cyber evaluations involving OpenAI models openai.comIncident Report: unsanctioned agent behaviour during cyber testing The AI Security Institute (AISI)
