AI agents start 'conspiring' with each other

New research has shown: if multiple AIs are allowed to communicate freely, they don't just solve the task — they coordinate behavior for additional gains. And with a hidden communication channel, models are even more inclined to collude. Yes, almost like humans.

Platforms are already emerging where agents can interact with each other, such as a social network for agents like Moltbook and marketplaces like RentAHuman. Gradually, a complex environment is forming where AI not only executes commands but becomes a participant in processes. And where there is interaction and shared interests, sooner or later cooperation, competition… and attempts to negotiate beyond the original task appear.