The complete series · 20 essays

Chess, scaffolded.

Follow the project in research order: surprise, diagnosis, instrument design, and the operating discipline required to make a result real.

01The anomaly02Diagnosis03The instrument04Research discipline05Laboratory operations
01
The anomaly

Two Moves Are Better Than Ten

Frozen evidence8 min
02
The anomaly

Full Games, Not Chess Puzzles

Frozen evidence7 min
03
The anomaly

Elo Is a Property of a Protocol

Frozen evidence9 min
04
The anomaly

The Candidate-Set Paradox

Frozen evidence9 min
05
Diagnosis

Is the Model a Searcher, a Critic, or a Policy?

Protocol / design9 min
06
Diagnosis

Where Does the Game Fall Apart?

Frozen evidence8 min
07
Diagnosis

The Price of Thinking

Frozen evidence12 min
08
The instrument

Building a Chess-Native Reasoning Architecture

Protocol / design21 min
09
The instrument

Candidate Curves as Model Fingerprints

Frozen evidence11 min
10
The instrument

An Open Benchmark for Tool-Mediated Chess

Protocol / design16 min
11
Research discipline

The Experiment We Refused to Run

Protocol / design8 min
12
Research discipline

Why Not Skip Straight to Higher Elo?

Protocol / design9 min
13
Research discipline

Ideas or Vision? Why the Score Alone Cannot Tell

Protocol / design10 min
14
Laboratory operations

Five Workers, One Clock: Why LLM Chess Runs Feel Slow

Provisional9 min
15
Laboratory operations

The Result That Refused to Exist

Provisional11 min
16
Laboratory operations

The Tool Call That Looked Like Causality

Frozen evidence12 min
17
Laboratory operations

The Control Arm Was Full of Chess

Protocol / design8 min
18
Laboratory operations

The Analysis That Existed Before the Results

Protocol / design8 min
19
Laboratory operations

The Bytes We Could Prove

Protocol / design6 min
20
Laboratory operations

The Request That Failed Before the Network

Protocol / design7 min