Signal #124186POSITIVE

Google DeepMind is worried about what happens when millions of agents start to interact

100

Google DeepMind is funding research into the potential dangers of millions of different AI agents interacting with each other online. According to Rohin Shah, who directs the company’s AGI safety and alignment research, the mass-market arrival of agents that can carry out tasks without human oversight and follow instructions given to them by other agents creates...

MIT Technology Review AIabout 4 hours ago
Read Full Article

Explore with AI-Powered Tools

View All Signals

Explore more AI intelligence

Want to discover more AI signals like this?

Explore Steek
Google DeepMind is worried about what happens when millions of agents start to interact | Steek AI Signal | Steek