6 changed files with 139 additions and 2 deletions
@@ -25,7 +25,9 @@ or write a daily briefing. It's meant to replace the n8n → Discord workflow.
 - **Paid articles and ads hidden**: heise+ and Golem `(g+)` are recognized by
  their title; SPIEGEL+ and t3n Pro by a marker in the article page, which the app
  checks once per new article in the background (it reads only until the marker,
-  and remembers results for 14 days). Sponsored posts (`Anzeige:`) are hidden too.
+  and remembers results for 14 days). Paid-subscriber posts from Substack newsletters
+  (Interconnects, Ahead of AI, …) are recognized in the feed itself, where Substack
+  cuts them off with a "Read more" link. Sponsored posts (`Anzeige:`) are hidden too.
  The feed header shows how many were hidden; both filters can be turned off.
 - **Ad and cookie-banner blocking** in the original-page view: requests to ~80
  ad/tracker hosts and the common consent managers (Sourcepoint, OneTrust,
@@ -9,6 +9,8 @@ import 'storage.dart';
 /// Recognizes paid and sponsored articles so the feed can hide them.
 ///
 /// Most paid articles are marked in the title (heise+, Golem's "(g+)").
+/// Substack newsletters cut paid posts short in the feed and end them with a
+/// "Read more" link to the post itself, so those are recognized from the feed.
 /// SPIEGEL and t3n only mark them in the page's schema.org data
 /// (`"isAccessibleForFree": false`), so for those sources each new article is
 /// checked once in the background and the result is remembered.
@@ -33,6 +35,14 @@ class PaywallService {
    caseSensitive: false,
  );

+  /// What Substack appends to a paid post's feed content in place of the rest:
+  /// `<p><a href="{post url}">Read more</a></p>`, as the very end. Free posts
+  /// end with their own text, even when they ask readers to subscribe.
+  static final _substackCut = RegExp(
+    r'<p>\s*<a href="([^"]+)">\s*Read more\s*</a>\s*</p>\s*$',
+    caseSensitive: false,
+  );
+
  static final _marker =
      RegExp(r'''"isAccessibleForFree"\s*:\s*"?(true|false)"?''', caseSensitive: false);

@@ -41,7 +51,11 @@ class PaywallService {
  static const _concurrency = 6;
  static const _keepFor = Duration(days: 14);

-  bool isPaid(Article a) => paidTitle.hasMatch(a.title) || (_checks[a.link]?.paid ?? false);
+  bool isPaid(Article a) =>
+      paidTitle.hasMatch(a.title) || _isCutSubstackPost(a) || (_checks[a.link]?.paid ?? false);
+
+  static bool _isCutSubstackPost(Article a) =>
+      _substackCut.firstMatch(a.contentHtml)?.group(1) == a.link;

  bool isSponsored(Article a) => sponsoredTitle.hasMatch(a.title);

@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Ahead of AI]]></title><link>https://magazine.sebastianraschka.com</link><generator>Substack</generator>
+<!-- Real items from https://magazine.sebastianraschka.com/feed (October 2026), content:encoded trimmed to its first paragraph and its end. -->
+<!-- Paid post (audience "only_paid" on its page): Substack cuts the content and ends it with a "Read more" link to the post. -->
+<item><title><![CDATA[Building an AI Text Detector From Scratch]]></title><description><![CDATA[An End-to-End Project With Dataset Construction, Model Training, Local Deployment, and RLVR]]></description><link>https://magazine.sebastianraschka.com/p/ai-detector-from-scratch</link><guid isPermaLink="false">https://magazine.sebastianraschka.com/p/ai-detector-from-scratch</guid><dc:creator><![CDATA[Sebastian Raschka, PhD]]></dc:creator><pubDate>Sat, 15 Aug 2026 11:54:24 GMT</pubDate><content:encoded><![CDATA[<p>Substack recently launched its AI detector feature in the UI, which is super interesting.</p><p>For this, we are going to fine-tune a DistilBERT classifier (similar to what I described in one of my early Substack articles, <a href="https://magazine.sebastianraschka.com/p/finetuning-large-language-models">Finetuning Large Language Models</a>), but more details on that later when we get to that stage.</p><p></p>
+      <p>
+          <a href="https://magazine.sebastianraschka.com/p/ai-detector-from-scratch">
+              Read more
+          </a>
+      </p>
+   ]]></content:encoded></item>
+<!-- Free post (audience "everyone") whose footer asks readers to become paid subscribers. -->
+<item><title><![CDATA[Controlling Reasoning Effort in LLMs]]></title><description><![CDATA[How LLMs Learn Low-, Medium-, and High-Effort Reasoning Modes]]></description><link>https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms</link><guid isPermaLink="false">https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms</guid><dc:creator><![CDATA[Sebastian Raschka, PhD]]></dc:creator><pubDate>Sat, 18 Jul 2026 11:16:09 GMT</pubDate><content:encoded><![CDATA[<p><span>It has been almost two years since OpenAI released o1, a model that popularized the idea of LLM-based reasoning models. DeepSeek-R1 followed about four months later, together with details of a reinforcement learning with verifiable rewards (RLVR) recipe to train such reasoning models.</span></p><p>If you liked my previous <a href="https://amzn.to/4fqvn0D">Build a Large Language Model (From Scratch)</a> book, this is essentially a sequel implementing inference-time scaling techniques and reinforcement learning algorithms from scratch.</p><p>And if you want to support future long-form articles like this one, consider <a href="https://magazine.sebastianraschka.com/subscribe">becoming a paid subscriber</a>. It helps me keep writing these independent deep dives and sharing the accompanying code, figures, and experiments.</p><p></p>]]></content:encoded></item>
+<!-- Free post (audience "everyone") that ends with Substack's subscribe widget. -->
+<item><title><![CDATA[GPT-6 Astra, Looped Transformers, and Hidden Reasoning]]></title><description><![CDATA[A Look at Recurrent Depth, Hidden Chains of Thought, and Recent Research on Looping Transformer Blocks]]></description><link>https://magazine.sebastianraschka.com/p/gpt-6-astra-looped-transformers-and</link><guid isPermaLink="false">https://magazine.sebastianraschka.com/p/gpt-6-astra-looped-transformers-and</guid><dc:creator><![CDATA[Sebastian Raschka, PhD]]></dc:creator><pubDate>Wed, 09 Sep 2026 11:14:25 GMT</pubDate><content:encoded><![CDATA[<p>A lot has happened in the last few weeks. I am sure that OpenAI&#8217;s GPT-6 Astra is top of mind for everyone right now. In particular, thoughts on its performance, the looped transformer/recurrent depth aspects, and rumors that Astra is &#8220;hiding&#8221; its reasoning trace (i.e., chain of thought).</p><div class="subscription-widget-wrap-editor" data-attrs="{&quot;url&quot;:&quot;https://magazine.sebastianraschka.com/subscribe?&quot;,&quot;text&quot;:&quot;Subscribe&quot;,&quot;language&quot;:&quot;en&quot;}" data-component-name="SubscribeWidgetToDOM"><div class="subscription-widget show-subscribe"><div class="preamble"><p class="cta-caption"></p></div><form class="subscription-widget-subscribe"><input type="email" class="email-input" name="email" placeholder="Type your email&#8230;" tabindex="-1"><input type="submit" class="button primary" value="Subscribe"><div class="fake-input-wrapper"><div class="fake-input"></div><div class="fake-button"></div></div></form></div></div>]]></content:encoded></item>
+</channel></rss>
@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Interconnects AI]]></title><link>https://www.interconnects.ai</link><generator>Substack</generator>
+<!-- Real items from https://www.interconnects.ai/feed (October 2026), content:encoded trimmed to its first paragraph and its end. -->
+<!-- Paid post (audience "only_paid" on its page). -->
+<item><title><![CDATA[Lessons from the hacks]]></title><description><![CDATA[Musings on model alignment, what determines safety, and where we go from here.]]></description><link>https://www.interconnects.ai/p/lessons-from-the-hacks</link><guid isPermaLink="false">https://www.interconnects.ai/p/lessons-from-the-hacks</guid><dc:creator><![CDATA[Nathan Lambert]]></dc:creator><pubDate>Sun, 09 Aug 2026 14:57:11 GMT</pubDate><content:encoded><![CDATA[<p><span>The recent run of cyberattacks by in-development frontier models has got me thinking a lot about how our current incentive systems are not well suited for such fast technological transitions.</span></p><div><hr></div><h4>Book sale</h4><p><span>I&#8217;m also hosting a book launch where you can get a free signed copy tomorrow from 5-8PM in Seattle (Fremont/Ballard area) &#8211; we still have some extra space so I&#8217;m opening signups to paid subscribers below the paywall:</span></p>
+      <p>
+          <a href="https://www.interconnects.ai/p/lessons-from-the-hacks">
+              Read more
+          </a>
+      </p>
+   ]]></content:encoded></item>
+<!-- Free post (audience "everyone") that mentions paid subscribers and ends with an embedded post's "Read more". -->
+<item><title><![CDATA[When will average people feel AI’s impact?]]></title><description><![CDATA[We&#8217;re <5 years into a compounding revolution which could take a century, and how the AI industry should manage this.]]></description><link>https://www.interconnects.ai/p/when-will-average-people-feel-ais</link><guid isPermaLink="false">https://www.interconnects.ai/p/when-will-average-people-feel-ais</guid><dc:creator><![CDATA[Nathan Lambert]]></dc:creator><pubDate>Wed, 09 Sep 2026 11:01:23 GMT</pubDate><content:encoded><![CDATA[<h5>Housekeeping: Paid subscribers to Interconnects now get a permanent 40% discount on my book when purchasing at Manning.com. Access the code at the Interconnects <a href="https://www.interconnects.ai/perks">perks page</a>.</h5><p>Many AI optimists tend to compare what is happening in this AI boom to the industrial revolution, or to other periods of rapid technological advancement and diffusion into society.</p><div><a class="embedded-post" native="true" href="https://www.fabricatedknowledge.com/p/mythos-and-engels-pause?utm_source=substack&amp;utm_campaign=post_embed&amp;utm_medium=web&amp;embedding_publication_id=48206"><div class="embedded-post-header"><span class="embedded-post-publication-name">Fabricated Knowledge</span></div><div class="embedded-post-title-wrapper"><div class="embedded-post-title">Engels' Pause and the Permanent Underclass </div></div><div class="embedded-post-cta-wrapper"><span class="embedded-post-cta">Read more</span></div><div class="embedded-post-meta">6 months ago &#183; 214 likes &#183; 5 comments &#183; Doug O'Laughlin</div></a></div>]]></content:encoded></item>
+</channel></rss>
@@ -0,0 +1,75 @@
+import 'dart:io';
+
+import 'package:daily_tech_news/models/article.dart';
+import 'package:daily_tech_news/models/news_source.dart';
+import 'package:daily_tech_news/services/feed_parser.dart';
+import 'package:daily_tech_news/services/feed_service.dart';
+import 'package:flutter_test/flutter_test.dart';
+import 'package:shared_preferences/shared_preferences.dart';
+
+import 'support/fake_app.dart';
+
+/// Serves saved Substack feeds (trimmed real items) instead of the network,
+/// dated an hour ago so every time window keeps them.
+class _SavedFeeds extends FeedService {
+  _SavedFeeds(this.fixtureByFeedUrl);
+
+  final Map<String, String> fixtureByFeedUrl;
+
+  @override
+  Future<List<Article>> fetchSource(NewsSource source, {String corsProxy = ''}) async {
+    final xml = File(fixtureByFeedUrl[source.feedUrl]!).readAsStringSync();
+    final anHourAgo = DateTime.now().toUtc().subtract(const Duration(hours: 1));
+    return [
+      for (final a in FeedParser.parse(xml, source))
+        Article(
+          title: a.title,
+          link: a.link,
+          source: a.source,
+          published: anHourAgo,
+          excerpt: a.excerpt,
+          contentHtml: a.contentHtml,
+        ),
+    ];
+  }
+}
+
+List<String> _titles(List<Article> articles) => articles.map((a) => a.title).toList();
+
+void main() {
+  final interconnects = testSource('interconnects', SourceKind.learning);
+  final substackNews = testSource('substack-news', SourceKind.news);
+
+  setUp(() => SharedPreferences.setMockInitialValues({}));
+
+  _SavedFeeds savedFeeds() => _SavedFeeds({
+        interconnects.feedUrl: 'test/fixtures/interconnects_feed.xml',
+        substackNews.feedUrl: 'test/fixtures/ahead_of_ai_feed.xml',
+      });
+
+  test('paid newsletter posts are hidden in the Learn tab and Today and counted as hidden',
+      () async {
+    final state = await launchApp([interconnects, substackNews], feedService: savedFeeds());
+
+    expect(_titles(state.articlesOf(SourceKind.learning)),
+        ['When will average people feel AI’s impact?']);
+    expect(state.hiddenCountOf(SourceKind.learning), 1);
+    expect(_titles(state.articlesOf(SourceKind.news)), [
+      'Controlling Reasoning Effort in LLMs',
+      'GPT-6 Astra, Looped Transformers, and Hidden Reasoning',
+    ]);
+    expect(state.hiddenCountOf(SourceKind.news), 1);
+  });
+
+  test('with "hide paid articles" off, paid newsletter posts show as before', () async {
+    final state = await launchApp([interconnects, substackNews], feedService: savedFeeds());
+
+    await state.updateSettings(state.settings.copyWith(hidePaid: false));
+
+    expect(_titles(state.articlesOf(SourceKind.learning)).toSet(),
+        {'Lessons from the hacks', 'When will average people feel AI’s impact?'});
+    expect(state.hiddenCountOf(SourceKind.learning), 0);
+    expect(_titles(state.articlesOf(SourceKind.news)), contains('Building an AI Text Detector From Scratch'));
+    expect(state.hiddenCountOf(SourceKind.news), 0);
+  });
+}
@@ -1,5 +1,8 @@
+import 'dart:io';
+
 import 'package:daily_tech_news/models/article.dart';
 import 'package:daily_tech_news/models/news_source.dart';
+import 'package:daily_tech_news/services/feed_parser.dart';
 import 'package:daily_tech_news/services/paywall_service.dart';
 import 'package:daily_tech_news/services/storage.dart';
 import 'package:flutter_test/flutter_test.dart';
@@ -38,6 +41,21 @@ void main() {
    expect(paywall.isSponsored(_article('Anzeigenmarkt bricht ein')), isFalse);
  });

+  test('recognizes paid Substack posts by the cut-off content in the feed', () async {
+    final paywall = PaywallService(await _storage(), client: MockClient((_) async => http.Response('', 500)));
+    final posts = {
+      for (final a in FeedParser.parse(
+          File('test/fixtures/ahead_of_ai_feed.xml').readAsStringSync(), _source()))
+        a.title: a,
+    };
+
+    expect(paywall.isPaid(posts['Building an AI Text Detector From Scratch']!), isTrue);
+    expect(paywall.isPaid(posts['Controlling Reasoning Effort in LLMs']!), isFalse,
+        reason: 'a free post asking readers to become paid subscribers');
+    expect(paywall.isPaid(posts['GPT-6 Astra, Looped Transformers, and Hidden Reasoning']!), isFalse,
+        reason: 'a free post ending with the subscribe widget');
+  });
+
  test('checks pages only for flagged sources and remembers results', () async {
    final storage = await _storage();
    final requested = <String>[];