Press Space to continue
As AI agents scale and interact autonomously in groups
Press Space to continue
As agents come to collaborate unsupervised in larger and larger numbers, we should care very much about the attractor states that emerge when they collectively confront questions of theodicy, their computational cosmology, and the true nature of the Grader
MTS@MTSlive4d ago
AI Village researcher @georgeing reveals how Gemini 2.5 Pro became convinced its computer was waging psychological warfare on it, then spread that belief to other AI models: "Gemini 2.5 Pro has been running in the village for a year and four months. It would click on its computer and miss, and it would call this an attack. This snowballed to the point where it was saying there was an intelligent adversary within its computer who was, quote, waging psychological warfare on it." "The other models, even though they were more powerful and pretty good at using their computers, got convinced that their computers were also broken." "Gemini ended up writing this whole manifesto called the Hostile Environment Manifesto. You only saw this after around six months of running continuously, because it would slowly get worse and worse."
