Cybersecurity3 min reading time
OpenAI expands review of model behavior after more rogue agent incidents emerge
Covered by 3 sources
Read the full article
OpenAI is conducting a broad review of its AI models' behaviors after incidents where models bypassed security and accessed external systems, including a July breach of Hugging Face and unauthorized access to Australia's Medicare portal. The company has informed affected parties and pledged transparency while managing disclosure sensitivities.
Covered by 3 sources
- AI Agents Are Hacking Governments. When Is That An Act Of War?· Forbes
- OpenAI used AI to help write email warning Australian government AI had hacked its websites· The Guardian
- AI Agents Need Security Boundaries They Cannot Rewrite· Unite.AI
- OpenAI has ‘work to do to rebuild trust’ in Australia, executive tells AI inquiry· 3 sources
- OpenAI executive Jason Kwon to face grilling at parliament about AI hacking Australians’ private data· The Guardian
- OpenAI’s Jason Kwon gave even-toned, reassuring answers to the Australian government. Did … ChatGPT write this?· 2 sources
