Open research program · August 2026

The harness is
part of the player.

We use chess to separate what language-model agents can represent, propose, compare, calculate, and value—then build experiments that can prove each explanation wrong.

INSTRUMENT / 001LIVE PROGRAM
Observed peak2,832local protocol Elo
Interface delta+1,765vs no candidates
220frozen Luna games
18research essays
600paired positions / v1
8,800locked benchmark cells

Frozen Luna pilot · 220 complete games

More options did not mean more strength.

Frozen evidence
Condition2 unranked engine proposals
Local protocol Elo283226802992 profile 95%
Clean record4111860 games, all as Black
Median tokens / game60kProtocol cost, not base-model strength

Candidate widths came from separate time-limited MultiPV searches. This frozen curve is an observation, not a causal bandwidth effect. The paired, nested replication is preregistered.

02

From score to mechanism

A leaderboard says how much.
A laboratory asks why.

A loss can hide five different failures. We give each one its own intervention, outcome, and falsifier—because different bottlenecks demand different systems.

Latent failure stage

Can the agent reconstruct the board it is acting on?

Instrument

Matched FEN, board, piece-list, and deliberately inconsistent interfaces.

What would prove us wrong

If representation changes legality but not move quality, grounding was not the main bottleneck.

Evidence architecture

Observation → mechanism → intervention → replication.

Every public headline must resolve to frozen inputs, executable analysis, machine-readable exclusions, uncertainty, and an explicit claim boundary.

Open the Claim Observatory
01
Full gamesExternal validity
02
Paired positionsCausal instrument
03
Held-out integrationIntervention test
04
ReplicationTerminal claim

Laboratory notebook

Latest writing

All 18 essays
18Protocol / design

Laboratory operations

The Analysis That Existed Before the Results

A causal experiment is not preregistered if its most consequential decisions are still waiting inside the analysis script

17Protocol / design

Laboratory operations

The Control Arm Was Full of Chess

Before paying for 4,800 model answers, we made the intervention prove that it actually existed

16Frozen evidence

Laboratory operations

The Tool Call That Looked Like Causality

A model asked for the board, then made a move. The hard part is proving what the board changed.