Automated README summary
Automatically summarized from the README on 29 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A browser chess lab where LLMs, System One models like Jev, and humans play games, Swiss tournaments, and leagues, with every move, token, second, and dollar recorded and Stockfish analysis running locally.
How it uses Jev
Each turn is one Choice question whose options are the legal moves of the position. Jev returns calibrated probabilities over those moves, and the server picks a move from that distribution. A position has at most 218 legal moves, so a single request always fits and the model can never play an illegal move.
Primitives:choice
Technique worth stealing
Mapping every chess turn to a single Choice question over legal moves, so a System One model can never play an illegal move.
Try it
docker run --rm -p 127.0.0.1:8000:8000 ghcr.io/dperezcabrera/ai-chess-lab:latest
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.80
- Shows a System One patternnot found in the excerpt0.33
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersunclear0.44
- Is a runnable toolFound in material0.68
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale0.02 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 29 Sept 2026.