Simulating institutions with LLM agents: strategy teams, investment committees, regulators
sanmikoyejo · x · 2026-10-11
yashsdave describes an experiment where LLM agents play institutional roles (strategy teams, investment committees, the regulator). Because markets, benchmark scoring, and incidents follow fixed rules, each channel of the institutional system can be varied one at a time.
More from Research
- Self-organizing agent teams hit 66.7% on math benchmarks vs 48.8% for their strongest member — zainhas · 2026-10-12
- OpenAI raises the plane's chromatic number lower bound to 6, Lean-formalized — fortnow · 2026-10-12
- Snorkel AI Expands Open Benchmark Grants 10x to $30M, Adds Red Team — ajratner · 2026-10-12
- How long is the coast of a neuron? Point-neuron abstraction may hide capacity — neurovium · 2026-10-12
- Community shrinks OpenAI Problem #190 obstruction from 66x66 to 3x4, verified in Lean — BorisMPower · 2026-10-12
- Autoresearch for LLM pretraining needs humans in the loop; stacked changes are the killer — menhguin · 2026-10-12