NewsBlur’s Intelligence Trainer has always had a simple rule: thumbs up beats thumbs down. If a story matches both a liked and a disliked classifier, the story shows up in Focus. That works well most of the time. But sometimes you run into a topic, author, or tag that you absolutely never want to see, and a regular thumbs down isn’t enough because a single thumbs up from another classifier overrides it.

Today I’m shipping two features that give the Intelligence Trainer more teeth: super dislikes that override any number of likes, and per-classifier notifications that ping you only when specific classifiers match.

Super dislikes are available to all users – free, Premium, Premium Archive, and Premium Pro. Folder and global scoping requires Premium Archive. Per-classifier notifications are exclusive to Premium Archive and Premium Pro subscribers.

Super dislikes

A super dislike is a new third state for classifiers. The regular thumbs down hides a story unless a thumbs up overrides it. The super dislike – shown as a double thumbs-down icon – overrides everything. If a story matches a super-disliked classifier, it’s hidden no matter how many positive classifiers it also matches.

The priority order is now: AI prompt classifiers > super dislike > thumbs up > thumbs down > feed score. This means super dislikes are the strongest manual signal you can set, second only to AI classifiers.

How to use it

In the Intelligence Trainer, every classifier pill now has three clickable icons on the right side: thumbs up, thumbs down, and the double thumbs-down for super dislike. Click the double thumbs-down to super-dislike a classifier. Click it again to remove the super dislike.

An explainer banner at the top of the trainer shows the priority chain so you always know how scoring works:

• Thumbs up beats any number of thumbs down
• Super thumbs down beats any number of thumbs up

Visual highlighting

Super-disliked classifiers are highlighted in a deeper crimson color, distinct from the regular red of a normal dislike. When you’re reading stories, you’ll see the same color treatment on matched titles, authors, tags, and text, with a small double thumbs-down icon inline so you can tell at a glance why a story was scored the way it was.

Works with scopes

Super dislikes work with all scope levels. Set a global super dislike on a topic like “sponsored” and it’s hidden across every feed. Set a folder-scoped super dislike on an author and they’re hidden in that folder regardless of positive training elsewhere. The same scoping rules from regular classifiers apply.

Per-classifier notifications

NewsBlur’s notifications have always been per-feed: turn them on and you get pinged on every new story. That’s fine for low-volume feeds, but not great for a high-volume feed where you only care about specific topics or authors. You end up choosing between too many notifications or none at all.

Now you can set notifications on individual classifiers. Every classifier pill in the Intelligence Trainer has a small bell icon. Hover over it and a popover appears with four channel toggles: Email, Web, iOS, and Android. Choose any combination, and when a new story matches that specific classifier, you get notified. Everything else in the feed stays quiet.

The bell icon lights up on classifiers with active notifications, so you can see at a glance which ones will ping you.

Works with scopes and regex

Classifier notifications respect the scope system. A notification on a global “breaking news” classifier fires when any feed publishes a matching story. A notification on a folder-scoped “earnings” classifier fires only for feeds in that folder.

Regex classifiers work too. If you have a regex title or text classifier, the notification evaluates the pattern with timeout protection on every new story.

Smart deduplication

If a story already triggered a feed-level notification on a channel, the classifier notification won’t duplicate it. Each story is sent once per channel, regardless of how many classifiers or feed rules it matches. There’s also a cap of 3 stories per classifier per update cycle, so a burst of matching stories won’t flood you.

Real-world examples

Breaking news alerts. Train “breaking” as a global title classifier, set it to notify via iOS and Email. You get a push notification whenever any feed publishes a story with “breaking” in the title.

Author tracking. Follow a journalist across multiple outlets. Train their name as a global author classifier with notifications, and you’ll know the moment they publish regardless of which feed it’s in.

Keyword monitoring. Use a regex classifier for a product name or company, scoped to your industry folder. Get an email when a matching story appears, without turning on notifications for every feed in that folder.

Availability

Super dislikes are available now on the web for all NewsBlur users. Per-classifier notifications are available on the web for Premium Archive and Premium Pro subscribers – all users can see the bell icon and popover, but toggling channels requires an Archive or Pro subscription.

If you have feedback or ideas for how to make these features better, please share them on the NewsBlur forum.

Resist and Unsubscribe

Not every website has an RSS feed. Some never did. Some had one years ago and quietly removed it. And some sites have content that updates regularly but was never structured as a feed in the first place: job boards, product listings, event calendars, changelog pages. Until now, if a site didn’t offer RSS, you were out of luck.

Web Feeds is a new feature that creates RSS feeds from any website. Point it at a URL, and NewsBlur analyzes the page structure, identifies the repeating content patterns, and generates extraction rules that turn the page into a live feed. It works on news sites, blogs, job boards, product pages, or really anything with a list of items that changes over time.

This is a huge feature and has been requested for years. I’m so thrilled to finally be able to offer it in a way that I feel comfortable with. Other solutions including having you select story titles on a re-hosted version of the page, but it was clumsy and error-prone. This way, we use LLMs to figure out what the story titles are likely to be, present the variations to you, and then let you decide what’s right. So much better!

How it works

Open the Add + Discover Sites page and click the Web Feed tab. Paste a URL and click Analyze. NewsBlur fetches the page, strips out navigation and boilerplate, and analyzes the HTML structure. Within a few seconds, you’ll see multiple extraction variants, each representing a different content pattern found on the page.

Progress updates stream in real-time while the analysis runs. NewsBlur typically finds 3-5 different extraction patterns on a page. The first variant is usually the main content (article list, blog posts, product grid), but sometimes the page has multiple distinct sections worth subscribing to. Each variant shows a label, a description of what it captures, and a preview of 3 extracted stories so you can see exactly what you’d get.

Select the variant that matches what you want to follow, pick a folder, and subscribe. NewsBlur will re-fetch and re-extract the page on a regular schedule, just like any other feed.

Story hints

Sometimes the initial best guess isn’t what you’re looking for. Maybe the page has a blog section and a job listings section, and you want the jobs. Click the Refine button and type a hint like “I’m looking for the job postings.” NewsBlur re-analyzes the page with your hint in mind and reorders the variants to prioritize what you described.

What gets extracted

For each story, NewsBlur extracts whatever it can find: title, link, content snippet, image, author, and date. Not every field will be available on every site, and that’s fine. At minimum you’ll get titles and links. The extraction uses XPath expressions, which means it’s precise and consistent across page refreshes as long as the site’s HTML structure stays the same.

When things change

Websites redesign. HTML structures shift. When NewsBlur detects that the extraction rules have stopped working (after 3 consecutive failures), the feed is flagged as needing re-analysis. You’ll see a feed exception indicator, and you can re-analyze the page with one click to generate updated extraction rules.

Use cases

Some examples of sites that work well with Web Feeds:

• Company blogs without RSS — Many corporate blogs dropped their RSS feeds years ago. Web Feeds brings them back.
• Job boards — Track new postings on a company’s careers page.
• Government sites — Follow press releases, meeting agendas, or public notices.
• Changelog pages — Monitor when a tool or service ships updates.
• Event listings — Keep tabs on upcoming concerts, conferences, or local events.
• Product pages — Watch for new arrivals or restocks on stores that don’t offer feeds.

Availability

Web Feeds are available to Premium Archive and Premium Pro subscribers. The ongoing feed fetching and extraction runs on NewsBlur’s servers like any other feed.

If you have feedback or ideas for improvements, please share them on the NewsBlur forum.

MORE ART (for your walls)

Signed Prints