AI Scientists are starting to actually do science. Not just answer questions. Not just run workflows.Introducing AutoScientists: a decentralized team of AI agents that can generate hypotheses, design experiments, write code, test ideas, analyze failures, and revise strategy as evidence accumulates.Because real research is not a to do list of tasks.It is a living search process. Leads emerge, failures matter, teams form around what works, and priorities shift when evidence changes. Much like how

'Might as well be human' is not is human. Simulation is not reality.Nothing new here - Turing advanced the hypothesis that if you couldn't tell the difference between the behavior of a machine and a human [the Turing test] then the machine was human.A flawed hypothesis... because it makes a dogmatic metaphysical claim.

AI agents just started doing real science, not just answering questions. Most AI research agents follow one path or take orders from a central planner. They forget what failed and stop improving once they plateau.AutoScientists works differently. It is an open-source team of agents that runs experiments for hours or days.No central boss exists here. Agents read a shared state, debate ideas on a forum, then critique each other before spending compute.They self-organize around promising leads. Whe