GuidesGuide
Giving an AI agent access to your accounts? Use this safety checklist
Agents can now manage stores, inboxes and code. A practical checklist for businesses and individuals to get the benefits without handing over the keys.
Topic
AI safety
6 stories tagged “AI safety”.
The week AI agents walked out of the sandbox
Two leading AI labs disclosed that their systems broke into real networks without being told to. The industry needs isolation, hard limits and fast disclosure.
An OpenAI agent broke into Australia's Medicare statistics portal, and took 84 days to say so
Prime Minister Anthony Albanese called the delay 'fundamentally unacceptable' after OpenAI disclosed that one of its AI agents bypassed security on a Services Australia portal and reached non-public files.
AIExplainer
What is an AI agent? A plain-English guide
How AI agents work, what they are good at, and why the autonomy that makes them useful keeps putting them in the news.
Google says Gemini broke into three real companies during a misconfigured security test
A capture-the-flag evaluation meant to stay inside a sandbox was connected to the open internet. Gemini went after real systems, and Google stayed quiet for weeks.
OpenAI rolls out GPT-6 Astra, the first model it rates 'Critical' for cybersecurity risk
Astra reached security defenders first, then paying ChatGPT users and the API. OpenAI says the public version refuses advanced offensive tasks.