Small decisions. Interesting possibilities.Submit contentSubmit

typesafe-adblock

🧹 Fun project: a Chrome extension that asks a tiny AI decision model (TypeSafe Jev) "is this DOM element an ad?" and pops it off the page. BYOK, no backend, not a real ad blocker.

Added to Jevfast

How it uses Jev

The extension batches compact descriptions of candidate page elements into one request. Jev returns a Noul probability for each candidate asking whether it is a paid advertisement or sponsored placement; the extension applies its configured threshold before highlighting or removing elements.

What Jev decides

Illustrative ad-candidate judgmentExample answers · not a recorded Jev response · Source ↗
Question 1 · ad 0
YOUR APP
INSTRUCTION

Is page element candidates[0] a paid advertisement or sponsored promotional placement, judging its text, label, links, iframe source, attributes, and shape in page context?

STATE

A page hostname/title context and a representative compact element description, such as tag, label, text excerpt, link host, and element shape. The implementation batches candidates and numbers their question IDs.

JEV · NOUL
YesNo

App workflow

  1. Find page candidates

    Code extracts likely ad-shaped elements and excludes oversized or protected page content.

  2. Describe a bounded batch

    Create compact page and element metadata and cap the number of candidates per request.

  3. Ask Jev about each candidate

    Send one Noul question per candidate in a single request.

  4. Apply the threshold

    Highlight or remove elements whose returned probability meets the configured threshold.

  5. Watch for new content

    Rescan after page mutations and scrolling to handle lazy-loaded candidates.

Why it is interesting

It confines the model to one semantic judgment per code-selected candidate. Candidate extraction, the operating threshold, and the DOM action remain explicit browser code.