factcircuit
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
Generative AI synthetic users negotiate in a simulated vegetable market testing whether a trained pricing policy (not LLM role-play) produces emergent social stratification
Translation pending
DataPython · HTMLGitHub @heatherluu99OnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Loading the full README. The saved excerpt is shown below.
Millbrook Market: A Closed-Loop Multi-Agent Environment for Behavioral Fidelity
Four interactive views in your browser — the market replayed, firms entering and leaving, 1,591 LLM decisions with their reasoning, and all 42 logged runs. No install, no server.
A synthetic consumer market built to find out when a simulated buyer can be trusted — and, more often, when it cannot.
Every phase writes down its question and its failure condition before it runs, and reports the answer either way. Most of the headline results are negative. Those are the ones worth reading.Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Millbrook Market: A Closed-Loop Multi-Agent Environment for Behavioral Fidelity
Four interactive views in your browser — the market replayed, firms entering and leaving, 1,591 LLM decisions with their reasoning, and all 42 logged runs. No install, no server.
A synthetic consumer market built to find out when a simulated buyer can be trusted — and, more often, when it cannot.
Every phase writes down its question and its failure condition before it runs, and reports the answer either way. Most of the headline results are negative. Those are the ones worth reading.Read the full README ↗