Automated README summary
Automatically summarized from the README on 4 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A companion repo to a LinkedIn post, testing Jev (TypeSafe AI's decision model) against Claude Haiku 4.5, Gemini 3.7 Flash and GPT-6 Luna on three text tasks: Google content categories, commercial intent, and keyword selection, using 1,000 CLINC150 user requests.
How it uses Jev
Jev receives the same prompt as a typed question. For categories and intent it uses Choice; for keyword selection it answers one Noul (yes/no) per candidate phrase in a single request. The returned choice and calibrated confidence are used directly in code.
Primitives:choicenoul
Technique worth stealing
Use Jev's calibrated confidence to route only uncertain cases to LLMs, saving cost and time.
Try it
uv sync; cp .env.example .env; set TYPESAFE_API_KEY; N_MESSAGES=20 uv run jupyter nbconvert --to notebook --execute notebooks/02-google-l1-categories.ipynb
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 projectunclear0.48
- Shows a System One patternnot found in the excerpt0.13
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolnot found in the excerpt0.05
- Top-10 learning shortlist signalnot found in the excerpt0.25
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.19 / 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 4 Oct 2026.