Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Hunch is a browser extension for anyone searching a web page. You type a word, question, or sentence, and the paragraph most likely to answer it lights up, with a probability shown; it also reports when the answer is absent.
How it uses Jev
For each page element, Hunch asks Jev a yes/no question like "Does this element describe X", with the element as state. Jev returns a probability per element; Hunch highlights the highest-probability elements and draws results on the scrollbar as they arrive.
Primitives:choice
Technique worth stealing
Chunk large pages into 160 blocks sent in parallel to fit Jev's 64k-token context window, rendering results as they return.
Try it
Build with npm run build, then load dist/chrome unpacked or dist/firefox as a temporary add-on; add a Typesafe API key in settings.
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 material0.90
- Shows a System One patternunclear0.59
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 2
- About JevFound in material0.97
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 21 Oct 2026.