Applied AI research. Building, running, and writing about multi-agent experiments.
The Roundtable
Multi-agent architectures
Research note
I'm researching how specialist AI agents produce better answers by disagreeing than any single model does by averaging. Inspired by Karpathy's LLM Council and the older economic idea that markets outperform planners, each experiment gives agents distinct personas, private incentives, and a visible budget — then studies what emerges when they're forced to argue instead of agree. The Roundtable is the first one.
Each agent is extended with personas, budgets, and an anti-convergence reward so the debate produces new ideas instead of consensus theater.
I am always looking to speak about papers, books & research. If you want to join — write to me: rr@beyondaiinstitute.com