Automated README summary
Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A toy harness that drives TypeSafe AI's Jev model character-by-character to produce chat replies, demonstrating that a classifier can be stacked into an autoregressive loop. Aimed at developers curious about Jev's limits.
How it uses Jev
Each step sends one choice question to POST /v1/systemone asking for the next character. The state carries the persona name, transcript, and assistant_reply_so_far. The chosen character is appended and resent; generation stops on end or max chars.
Primitives:choice
Technique worth stealing
Stack a single-shot choice classifier into a next-character loop, with decoding rules (repeat penalty, stopping thresholds) layered on top of the distribution.
Try it
Node 18+, no dependencies: git clone, npm start, open http://localhost:8787, paste your TypeSafe API key.
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 projectnot found in the excerpt0.36
- Shows a System One patternFound in material0.87
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersFound in material0.98
- Is a runnable toolFound in material0.62
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale0.01 / 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 6 Oct 2026.