# Limitations (living document; mirrors paper/sections/limitations.tex)

1. **Efficiency benchmark is second-order and price-taking.** Proposition 3 holds in the LQ approximation with complete
   markets and symmetric ownership; market power of model providers, non-pecuniary spillovers and higher-order terms break it
   (Prop. 4a gives the direction).
2. **Which decision is delegated is assumed.** Savings mapping has no stake (kappa0 = -0.0015); the portfolio mapping is the
   baseline. Firm-level input decisions (David–Hopenhayn–Venkateswaran channel) are not modelled.
3. **Information parameters are illustrative** (sigma_theta_R, sig_H_R, sig_A_R, M, kappa, tau_s, qbar; Model B return noise;
   Model C dividend/noise/market-maker parameters). Levels of welfare effects are orders of magnitude, not estimates.
4. **Model B has no aggregate risk**; it isolates cross-sectional channels; top-1% share too low (standard Aiyagari limitation).
5. **Model C is a laboratory**: temporary trading equilibrium per period, market maker ladder as liquidity, 8–20 agents.
   The margin-spiral channel (H4) could not be reproduced in the lab: transient model errors mean-revert once dividends fail to
   confirm them, and the mechanical margin rule deleverages agents at the first breach; see results_c.tex for the numbers.
6. **LLM agents are not humans**: three small 4-bit open-weight models, prompt/temperature dependence, logged; results are
   about the architecture, not about deployed commercial agents.
7. **No external causal identification**; validation roadmap in calibration.tex.
8. **Independent-AI-principal counterfactual** implemented but not reported (no institutional benchmark).
9. **Engineering caveats**: the Walrasian call only clears among submitted limits (no price when one side is empty);
   CDA prices are last-trade prices (stale when no trade); the owner class in Model B is outside the household block.