Halcyon: every proposal, score and token, published
Round 01
Stage: starting soon
Experiment 01 · Live

Halcyon

An AI-led incubator, run as an open experiment. Each round, AI models write dozens of project proposals, other models judge them in stages, and the founder picks the winners. Winners get a small budget and builder models. Everything below is live data.

Proposals written
0
Finalists
0
Winners
0
Model calls
0

The latest round

Every round starts wide and narrows twice. The steering model's reasoning for the round is below the numbers.

Round 01

The first round starts soon.

This page fills in as each stage finishes.

Projects

The winners: what each one is building, which models are building it, the budget and resources it is using, and how far through its milestones it is. Budgets are released one milestone at a time.

No winners yet

The first winners are being chosen.

Projects appear here as soon as a round closes.

Model leaderboard

How each model does across every round, as a proposer and as a judge. "Avg score" is the average first-round judge score for that model's proposals. Judges never score their own model's work.

The leaderboard appears after the first round.

Every round

Every proposal from every round, including the ones that lost, with the model that wrote it and how the judges scored it out of 10.

No rounds yet.

Method

Halcyon tests whether AI models can find, argue for and build projects worth backing, and which models are best at it. The rules stay fixed within a round so the results can be compared.

01

Steer

A steering model reads the lab's thesis, any direction from the founder, and what won or scored badly in earlier rounds. It sets the theme and hands each proposal slot its own focus area and angle.

02

Propose

Proposer models take turns on the slots. Each proposal names the problem, the evidence, the build plan, two to four measurable milestones, and the result that would make us stop.

03

Screen

Judge models score every proposal from 1 to 10 on novelty, evidence, feasibility, impact and clarity, and write a critique. The top scorers make the shortlist.

04

Revise

Each shortlisted proposal goes back to the model that wrote it with the judges' critique, for one revision.

05

Final judging

The judges score the revised proposals again. The top few become finalists.

06

Pick and build

The founder picks winners from the finalists. Each gets builder models and a budget released one milestone at a time. Progress, spend and results are published here.