Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Tampermonkey userscript for X (Twitter) users that folds away engagement-bait, promotional posts, politics, showbiz, and paid ads from the timeline, using TypeSafe's Jev decision model through OpenRouter, TypeSafe, or a self-hosted endpoint.
How it uses Jev
Each queued post becomes one compact string with author name and verification type. The request state holds each enabled filter's definition once; each post gets one yes/no noul question per enabled filter. Jev returns a probability per post per filter; posts at or above the filter's threshold are collapsed or removed.
Primitives:noul
Technique worth stealing
Put filter definitions once in state and ask one short noul question per post per filter, batching up to 32 posts per request.
Try it
Install Tampermonkey, open tolerable-x-feed.user.js, pick a provider, paste a key, and click Test connection on x.com.
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 excerpt0.23
- Shows a System One patternnot found in the excerpt0.33
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.10
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalnot found in the excerpt0.12
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale0.99 / 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 4 Nov 2026.