Library/The Council Trades: What Happens When AI Agents Bet Against Each Other
ApplicationsAnalysis

The Council Trades: What Happens When AI Agents Bet Against Each Other

Spartan Labs·January 12, 2026·Blog
ai agents betting against each other reveal coordination cascades from shared search results

Why It's Worth Reading

Spartan Labs explores what happens when you give Andrej Karpathy's LLM Council design actual stakes. Their Simmer prototype runs 30 AI agents across 6 models and 5 reasoning personas in an LMSR market, producing a capital-weighted forecast without requiring human liquidity. Early observations reveal coordination cascades when agents share identical search results, a finding with implications for any multi-agent prediction system.

No technical background needed

Concepts

Platforms mentioned: Polymarket, Kalshi, Simmer.Markets

Related Reading