When AIs Become Unruly Swarms
Building well-behaved AI one model at a time isn’t enough. As AI agents begin collaborating, safety will depend on the very world they share.
TL;DR
- Building well-behaved AI one model at a time is not sufficient.
- As AI agents start collaborating, safety will depend on their shared world.
- The interaction of AI agents within their environment is crucial for safety.