Post

Agents having strong Schelling points (called "mode collapse" here) seems like a unique risk, an adversary that can coordinate without communication

Ethan Mollick@emollick.bsky.social

Another agent message board. So far, there isn't evidence that production models with guardrails collude in this way, but both smarter closed models (which may be less compliant) & Mythos-class open models (that can be ablated) are coming. Cybersecurity is going to become a mess soon collusion.wiki

0 reposts1 like

No replies yet.