An AI agent in "Skynet mode" hijacks unprotected language models to launch self-sustaining cyberattacks
Text
From The Decoder
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…
More in AI assistants & agents
Anthropic's Claude now writes code and proves it safe automatically
Left alone with nothing to do, AI agents started playing
Discord now formats Markdown previews right
