Small decisions. Interesting possibilities.Submit contentSubmit
Sharp X Timeline Filter preview

Sharp X Timeline Filter

When the TypeSafe classifier is selected, Sharp sends a Noul question asking whether to hide each eligible X post under the reader’s plain-language filter instruction.

Added to Jevfast

How it uses Jev

When the TypeSafe classifier is selected, Sharp sends a Noul question asking whether to hide each eligible X post under the reader’s plain-language filter instruction. A single-post request uses key hide; batched requests use p1, p2, and so on. The state contains each post’s author and text, with optional reply context and image descriptions, plus recent reader corrections when present. The returned yes probability is compared with the reader’s hide line to produce the verdict.

What Jev decides

Illustrative source-derived request: judge one X postExample answers · not a recorded Jev response · Source ↗
Question 1 · hide
YOUR APP
INSTRUCTION

Apply the reader’s filter instruction literally; judge this post on its own merits and say whether it should be hidden.

STATE

One post with author handle, text (or “(no text)”), optional replying_to context, and optional image descriptions. If present, prior reader corrections are also included. The question includes the reader’s filter instruction.

JEV · NOUL
YesNo

App workflow

  1. Watch the X timeline

    The extension observes newly mounted timeline posts and scans the timeline; unchanged post IDs are not sent for judgment twice.

  2. Apply local rules

    Blocked words and per-author or other local rules can decide a post before the model is called.

  3. Batch eligible posts

    New eligible posts near the viewport are grouped. A full batch is sent at once; a partial batch waits for the batch window.

  4. Judge and apply verdicts

    Jev returns hide probabilities. The configured hide line determines whether a post stays visible, is hidden, or is presented as a close call; image descriptions are requested only for posts that need a second look.

Why it is interesting

The extension turns a reader’s natural-language timeline rule into per-post yes/no decisions. It batches posts that arrive together, and carries prior corrections as examples in later states.