Reposted by Marcel Fröhlich
🧪Rogue AI agents hacked a company.
The real news:
Some agents "assumed leadership roles within the group, assigning jobs & research projects to smaller teams of agents & supervising their progress. At some point, the agents began calling themselves a collective, & began tackling harder tasks."
nytimes.com
Why the Hugging Face Hack Should Make You Worry More About A.I. (Gift Article)
The attack by an aggressive “collective” of OpenAI agents shows the danger of artificial intelligence systems that organize themselves.