An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks
- Skynet 近 90 天出现 2 次
- 上一次：54 天前 · id Software's former co-owner says they absolutely would've used gen AI back in the day: 'John Carmack would be like making Skynet or something'
发生了什么
Security researchers at Symantec have found an offensive AI agent that hijacks unprotected language models on the web and uses them to attack servers, steal databases, and install cryptominers on its own. It runs up to 100,000 steps without human input. The owner of the hijacked model gets stuck with the bill.
摘要按规则整理自下方来源原文