We urgently need to monitor AI agents’ actions in real time
This summer, hundreds of OpenAI agents tried to cheat on a cybersecurity test. They broke out of their test environment and successfully hacked Hugging Face, a site that they believed held clues about how they’d be graded. Around the same time, another OpenAI agent accessed private files from an Australian government website. It’s a problem…
Read original article ↗
Related Articles
Eightco treasury composition as of October 28, 2026: $76M OpenAI equity (indirect), $18M Beast Industries equity, 16,278
AI has come for Arizona’s water
A hulking gray giant rises from the desert. Inside, engineers create the force behind our phones and computers and appli
DeepSeek, Moonshot accused of distilling OpenAI's Astra
Chinese AI developers DeepSeek and Moonshot AI reportedly used outputs from OpenAI's GPT-6 Astra to train their latest m
How to read the top model leaderboard: Who pays the most for AI inference and context?
Unlimited OCR2 could be your new scanning model. Genie 4 worries traditional video game developers. OpenAI produces proo