Automated README summary
Automatically summarized from the README on 17 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A small lab for System One models—AI engines that return typed decisions with probabilities in one forward pass. It teaches and runs open-weights equivalents of TypeSafe's Jev for free, with runbooks, lessons, and experiments for humans and AI agents.
How it uses Jev
The README does not describe Jev being used in code. It presents Jev as the famous closed model in the System One class and runs open-weights equivalents (Rizzo Flow, Laya) that return the same JSON contract for categorization decisions.
Primitives:choicescorenoul
Technique worth stealing
Use a single forward pass to return typed decisions with calibrated probabilities instead of generating text.
Try it
Run start.sh or follow RUNBOOK.md: install uv, clone rizzo-flow, uv sync, download, serve.
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 material0.86
- Shows a System One patternnot found in the excerpt0.14
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.11
- Is a runnable toolunclear0.58
- Top-10 learning shortlist signalnot found in the excerpt0.32
- Is a replica of the modelFound in material0.93
- Solves a common problem (0–2)score on a 0–2 scale0.91 / 2
- About JevFound in material0.94
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 17 Oct 2026.