Automated README summary
Automatically summarized from the README on 9 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A hands-on tutorial benchmarking open-source System One (Jev-style) decision models zero-shot on four tasks: tweet sentiment, Snake, Finnish understanding, and Snake from images. For developers evaluating these models on a 32 GB Apple M5.
How it uses Jev
Jev models answer typed questions with probabilities instead of generating text. In the sentiment test, each tweet is classified with a choice question (negative/neutral/positive). In Snake, each move is one choice question per tick, asked six different ways. Finnish uses choice questions on four datasets. The vision test uses choice questions about the board and moves.
Primitives:choice
Technique worth stealing
Zero-shot evaluation of decision models using typed choice questions, comparing probabilities against LLM baselines.
Try it
Run uv run python docs/page/build.py, docs/snake-report/build.py, docs/finnish-report/build.py to generate reports.
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 material0.87
- Shows a System One patternunclear0.53
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.13
- Is a runnable toolnot found in the excerpt0.18
- Top-10 learning shortlist signalunclear0.56
- Is a replica of the modelFound in material0.72
- Solves a common problem (0–2)score on a 0–2 scale0.34 / 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 9 Oct 2026.