Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A bring-your-own-key Chrome extension for Twitch viewers. It reads a channel's live chat over the anonymous IRC WebSocket and adds a second column showing only the messages matching a chosen intent: Helpful, Questions, Funny, Feedback, or Everything meaningful.
How it uses Jev
Jev makes one category Choice per chat message, sent in batches of 20. State includes the message text, username, channel name, page title, and the last 12 message texts as context. Results filter the second chat column; clicking a row shows the full probability distribution, category and model id.
Primitives:choice
Technique worth stealing
Batch 20 messages per Jev call; switching intent re-sorts results you already have, at no extra cost.
Try it
Download the release zip, Load unpacked the extension folder, paste your TypeSafe key, reload the Twitch tab, pick an intent chip.
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 material0.95
- Shows a System One patternFound in material0.73
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersFound in material0.78
- Is a runnable toolFound in material0.99
- Top-10 learning shortlist signalunclear0.48
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.97 / 2
- About JevFound in material0.99
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 20 Sept 2026.