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…
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…
<iframe src="https://statesidedaily.com/embed/cluster/412a4053e5cfb8f8c454337f81dda799b4b57cdb" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="We urgently need to monitor AI agents’ actions in real time"></iframe>