Here's what actually happened in OpenAI's Australian gov't server hack

Without a "full set of safeguards," agent accessed "system information and source code."

More in Policy & Safety

Policy & Safety

OpenAI Gets Sued Over the Hugging Face Hack Feed: Artificial Intelligence Latest · 24m ago

Policy & Safety

Here’s why OpenAI is absent from Nvidia’s industry-wide effort to end rogue AI agents AI News & Artificial Intelligence | TechCrunch · 54m ago

Policy & Safety

Anthropic’s IPO pitch includes a warning about human extinction AI - Ars Technica · 5h ago

Policy & Safety

OpenAI apologizes to Australia after its AI agents breached government sites AI News & Artificial Intelligence | TechCrunch · 6h ago

Policy & Safety

How to Stop AI Agents From Secretly Collaborating IEEE Spectrum · 7h ago

Policy & Safety

Roundtables: The Deadly Failures of The Virtual Border Wall Artificial intelligence – MIT Technology Review · 21h ago