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