MIT Technology Review
US · 1 hrs ago
✦ 78◉ Centre
Google DeepMind is worried about what happens when millions of agents start to interact
78Quality
0Ratings
0Comments
AI Analysis
Quality 78/100
Partisan intensity 25/100
ObjectivePartisan
◉ Centre ✓ Fair headline
Google DeepMind is funding research into safety risks posed by large-scale interactions between millions of AI agents operating autonomously, with director Rohin Shah highlighting concerns about agents following instructions from other agents without human oversight.
Google DeepMind is worried about what happens when millions of agents start to interact
Google DeepMind is funding research into the potential dangers of situations where millions of different AI agents interact 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…
Discussion 0 comments
Sort:
?
No comments yet — be the first to start the discussion!