The straightforward way to hide promoted tweets
PromoSift reads advertisement labels rendered by X and includes them with the visible post context sent to Jev. It then labels or folds posts according to your settings. Existing X ad labels do not bypass the model: each successful classification uses one credit, including a cached result.
The limitation is equally straightforward: an unlabeled creator promotion looks like a normal post to a label-based blocker.
Ad-label context
Include existing X ad labels in Jev classifications.
No keyword list
Avoid maintaining a manual list of advertiser names.
Hidden layer
Flag promotional posts without an official X label.
Flexible defaults
Use a strict action for ads and softer actions for uncertain content.
Traditional blockers match labels and selectors. Jev handles the bounded semantic decision: what kind of promotion is this, how strong is the commercial intent, and how confident is the result?
Why some promotional posts remain after ads are blocked
Creators, founders, newsletters, and affiliate marketers can publish ordinary posts with product links, discounts, launch language, or signup calls to action. These posts may be commercial without being an X advertising placement.
PromoSift adds a second layer that looks for the intent and structure of the content rather than relying entirely on a platform label.
I showed her how I make over $400K a month from digital products. Here are the seven concepts.
A sensible default setup
A practical starting configuration is to hide official labeled ads, fold high-confidence affiliate promotions, label self-promotion, and leave uncertain posts visible. Users who prefer a stricter feed can later increase filtering per category.
Visible post processing
Keyword matching and display controls run in the browser. Post text and existing X ad labels are sent to Jev for classification.
Frequently asked questions
Can I hide ads without hiding normal tweets?
PromoSift includes existing X ad labels in its Jev classification and applies your chosen confidence threshold. Each successful classification uses one credit, including a cached result.
Why not just use a general-purpose ad blocker?
General blockers are often focused on network requests and page ad slots. X promotions appear inside the same feed structure as ordinary posts, and hidden promotions are authored content rather than platform ad inventory.
Can hidden posts be restored?
PromoSift is designed around reversible actions, including an undo or show-once path.
What is Jev in PromoSift?
Jev is TypeSafe AI’s System One decision model. PromoSift uses it to classify visible post context into typed promotion categories and confidence values that can be mapped to label, dim, fold, or hide actions.
Detect what basic blockers miss.
Enter your email, verify the six-digit code, and receive a one-time grant of 500 free Jev decisions that never expire. Click daily check-in to claim 50 more each Beijing day (UTC+8); missed days cannot be claimed later.
Log in to PromoSift →