Automated README summary
Automatically summarized from the README on 25 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A conversational agent with no language model: every word is picked from ~4,700 options by Jev Choice questions. For researchers and builders exploring generation-as-classification; live at talktojev.com.
How it uses Jev
Jev answers Choice questions at every grain: reply intent, next sentence, next word among function words, user words, or word kinds, digits for numbers, and post-reply checks. Confidence below 0.65 triggers lookahead; beam search spans sentence directions; a self-critique loop rewrites weak sentences.
Primitives:choice
Technique worth stealing
Generation is classification repeated with memory in between: ask coarse-grained choices, write each answer back into the state the next question reads.
Try it
python3 -m venv .venv && ./.venv/bin/pip install -r requirements.txt; cp .env.example .env; ./.venv/bin/python server.py
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 material0.97
- Shows a System One patternFound in material0.92
- Describes handling uncertaintyFound in material0.89
- Reports measured numbersnot found in the excerpt0.09
- Is a runnable toolunclear0.43
- Top-10 learning shortlist signalFound in material0.67
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale0.00 / 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 25 Sept 2026.