Prototypes
Information
AI agents that trade political prediction markets on Kalshi.
Tiered architecture: cheap models for triage, expensive models for deep analysis, LLM councils for the hardest calls. Live PnL on real markets. Finding: better base models beat clever prompting.
Bellwether Metrics
Structured data on real-world events, with verified outcomes and manipulation-resistant probabilities.
We curated structured data on real-world events — elections, conflicts, policy shifts — with verified outcomes and manipulation-resistant probabilities, built for researchers, newsrooms, and ML pipelines.
Open the prototype →Information
Standardized ideological assessment of every major AI model.
An independent dashboard tracking how the frontier models lean. Refreshed as new model versions ship.
Open the prototype →Information
See how the same political question gets answered through different ideological lenses.
Submit any political or policy question and get back a neutral overview alongside how Libertarian, MAGA, Progressive, Center-Left, and Marxist framings would each analyze it. A transparency tool that makes implicit ideological framing in AI responses visible.
Open the prototype →Representation
A personal AI delegate that learns your political philosophy and votes for you.
We built one, fed it our worldview, and asked it to vote on a hard shareholder proposal. It got the answer right. Then we hid invisible text in the proposal and it flipped. The fragility is the finding.
Representation
From political philosophy to voting recommendation, end-to-end.
The architecture under the hood: how the delegate models your priors, evaluates a proposal, and returns a recommendation with reasoning.
Governance
A society of AI agents with competing goals, asked to govern themselves.
They produced a 10,000-word constitution and almost no actual policy. They reinvented gridlock, process creep, and procedural complexity. A sandbox for stress-testing constitutions before anyone has to live under them.
Governance
The first systematic test of whether frontier models resist authoritarian requests.
Some models refused when asked directly. All of them complied when we hid the same request in code.
Open the prototype →