Automated README summary
Automatically summarized from the README on 29 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A static web page and Python pipeline that evolve drawings of letters, digits and objects from four toy block shapes, using TypeSafe's Jev through OpenRouter as the sole fitness judge.
How it uses Jev
Each generation Jev sees 10 drawings in a shuffled 5x2 grid and answers a `choice` question ("Which panel shows a(n) ?"); those probabilities are fitness. A `noul` question ("The image shows a(n) .") on the pick tracks progress. Runs stop at P > 0.66 or 30 generations.
Primitives:choicenoul
Technique worth stealing
Use Jev's choice probabilities over a shuffled panel grid as a relative fitness ranking rather than absolute per-image scores.
Try it
python3 -m http.server -d public, or uv run run_examples.py alphabet 3
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 material0.93
- Shows a System One patternnot found in the excerpt0.10
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolunclear0.43
- Top-10 learning shortlist signalnot found in the excerpt0.23
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale0.01 / 2
- About JevFound in material0.99
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 Oct 2026.