I took the @karpathy autoresearch loop and pointed it at markets.
25 AI agents debate macro, rates, commodities, sectors, and single stocks daily. Every recommendation scored against real outcomes. Worst agent by rolling Sharpe gets its prompt rewritten by the system. Keep or
Post describes an AI-driven market research loop where multiple agents debate macro and stock ideas, score recommendations against outcomes, and auto-rewrite underperforming prompts.
