What My Dead RSS Reader Revealed About My Digital Past

Image of black framed glasses on a black surface.

While researching for another entry for this blog and deep diving into my old files, I came across my long lost Google Reader Takeout export. For me, Google Reader was the RSS Reader until July of 2013 when it was shuttered. In anticipation of this shutdown, Google did provide a method of exporting your data into a set of JSON files. Honestly, I had forgotten that I had collected my data since, at the time, I wanted only to continue reading my feeds (something I do to this day).

Having stumbled upon this extract, I was curious to explore this time capsule of my reading habits. Thankfully, technology has come a long way in the decade since I collected my extract and we have tools like LLMs now. They’re great at summarizing data. I thought I would share my conversation with Anthropic’s Claude with you, kind reader.

A Conversation with Claude about my Google Reader Habits

Me

The attached files were the result of Google Takeout extract from my Reeder account. Describe the content of each of the files.

Claude

I'll analyze each of the Google Reader Takeout files for you:

followers.json

Contains data about people who followed your Google Reader activity. The file shows one follower.

following.json

Contains data about people you followed in Google Reader.

shared-by-followers.json

Contains items that your followers shared with you. The structure shows:

notes.json, shared.json, starred.json, subscriptions.xml

These files weren't displayed in the document content, but based on typical Google Reader Takeout exports: – notes.json: Would contain your personal notes/annotations on articles – shared.json: Would contain items you publicly shared – starred.json: Would contain articles you starred/saved – subscriptions.xml: Would contain your RSS/Atom feed subscriptions (OPML format)

Would you like me to examine the content of those other files?

Me

Yes, please examine the content of the other files.

Claude

Complete Analysis of Google Reader Takeout Files

notes.json

Contains your personal annotations on 7 articles from 2008-2011. Your notes reveal interests in: – Productivity: Commentary on the 80/20 Principle and Four Hour Workweek – Tech/Security: Notes on Firefox vs IE, wireless security in Perth – Space/Science: Enthusiasm for watching shuttle launches (“Go outside and see the shuttle take off!!”) – Comics: Reference to “Hackers” movie in xkcd comic (“Extra points for the Hacker's reference!”) – Infrastructure: Concern about undersea cable cuts (“Again?”) – Travel: Wanderlust (“Makes me want to travel more”) – Movies: Comment on Iron Man vs Batman (“Iron man for the win! Tony Stark can totally kick Bruce's ass”)

Timestamps range from December 2008 to May 2011.

shared.json

Contains 29 items you publicly shared with others from 2008-2011, covering diverse interests: – Productivity: Parkinson's Law, time management, organizational tips – Technology: Gmail security features, cloud services, search engines – Security: Cybersecurity legislation, Internet Explorer vulnerabilities, RFID concerns – Travel: Articles from Gadling about destinations like Raleigh NC – Science: NASA missions, technology in education – Digital Rights: Multiple articles about DRM, e-book ownership, Amazon Kindle controversies – Pop Culture: Dark Knight/Blu-ray sales, various tech product reviews

The last update was July 2011. Notably includes Cory Doctorow's article about Amazon remotely wiping Kindles.

starred.json

Contains 83 starred articles from 2008-2013, representing content you wanted to save. Categories include: – Tech Products: Google Reader shutdown announcement (March 2013, appropriately the last item) – Privacy/Security: DRM issues, Amazon Kindle account closures, cybersecurity – Digital Rights: Strong focus on e-book ownership, copyright, open access – Science/Tech: Various technology news and reviews – Practical Advice: Productivity tips, tech tutorials

subscriptions.xml (OPML format)

Your RSS feed subscriptions organized into 10 categories with 61 total feeds:

Travel (7 feeds): Gadling, Go See Run Eat Drink, Intelligent Travel, Digital Nomad, Vagabondish Tech Security (4 feeds): SANS Internet Storm Center, US-CERT, Defense Tech, Wired Danger Room Apple News (4 feeds): AppleInsider, Patently Apple, TUAW Magazine (9 feeds): Boing Boing, Lifehacker, MAKE Magazine, Smitten Kitchen, xkcd Entertainment (7 feeds): Hyperbole and a Half, Questionable Content, Pandora stations Tech News (4 feeds): TechCrunch, The Verge, BBC Technology, Google Blog General News (1 feed): Al Jazeera English Stuff (4 feeds): Cool Tools, Uncrate, Gear Patrol, GearJunkie Probation (10 feeds): Various feeds on trial including Evernote, PetaPixel, Technology Review Individual Feeds (11): Google Apps Status, Brooksfield School blog, W&OD Trail Report

The subscription mix shows strong interests in technology, security, productivity, travel, and maker/gear culture, with an emphasis on alternative/independent media sources.

Me

List the urls of all of the articles that i shared.

Claude

Here are all 149 URLs from the articles you shared in Google Reader (2008-2011):

List of 149 URLS

Me

Does the shared json file include the dates that I shared the articles?

Claude

Yes! The shared.json file includes timestamps for when you shared the articles. There are multiple timestamp fields:

  1. published – The article's original publication date (when it was written)
  2. crawlTimeMsec – When Google Reader crawled/processed the item, which represents approximately when you shared it
  3. timestampUsec – More precise version of the crawl time

The crawlTimeMsec field is the most reliable indicator of when you actually shared each article. As you can see from the examples, sometimes you shared articles on the same day they were published (like the 80/20 Principle article), and sometimes you shared them days later (like the Raleigh travel article, published July 14 but shared July 17).

Would you like me to create a list with both the share dates and the article URLs?

Me

Create a CSV files that includes the URL, the published date, and the date I shared that article.

Claude

[View your CSV file].

The CSV file contains all 149 articles you shared with columns for Title, URL, Published date, and Shared date.

Me

Based on the URLs, which sites did I share from most frequently?

Claude

Based on the URLs, here are the sites you shared from most frequently:

Top 10 Sites:

  1. Lifehacker – 67 articles (45% of all shares)
  2. Feedproxy (various sources) – 16 articles
  3. Wired – 16 articles
  4. TreeHugger – 5 articles
  5. xkcd – 5 articles
  6. Seclists.org (InfoSec News) – 5 articles
  7. Gear Patrol – 4 articles
  8. Gizmodo – 4 articles
  9. New York Times – 4 articles
  10. ISC SANS – 3 articles

Key Insights:

Me

Looking at the date stamp of of my shared links, look for any interesting patterns. Example questions include: did I share mostly within a certain range of hours or days of the week? what about seasonally? What day did I share the most? Looking at the source, did I share from some sources only during specific times and not in others? Look for anything that might be interesting.

Claude

Here are the interesting patterns I found in your sharing behavior:

KEY FINDINGS

1. You Were a Night Owl / Evening Sharer – Peak sharing hours: 5pm-8pm (19:00 had 19 shares – your busiest hour) – 63 shares (42%) happened in the evening (5pm-midnight) – Significant late-night activity: 32 shares between midnight-6am – Almost zero sharing during work hours: 6am-10am had ZERO shares

2. Strong Weekday Preference – 85% of sharing happened Monday-Friday – Monday was your biggest day (32 shares) – Weekend sharing was minimal (only 23 shares total) – This suggests sharing was often part of your workday browsing routine

3. December Was Your “Sharing Season” – December: 34 shares (23% of all shares in one month!) – February: 23 shares (second place) – Summer months (May-August) were quieter – This December spike likely reflects holiday downtime and catching up on reading

4. 2009 Was Your Peak Year – 2009: 83 shares (56% of all shares) – 2008: 41 shares – 2010: Sharp drop to only 23 shares – 2011: Only 2 shares (you essentially stopped)

5. Lifehacker Evolved with Your Habits Lifehacker dominated 2009 (44 shares) but dropped dramatically in 2010 (6 shares), mirroring your overall decline in sharing activity.

6. “Burst” Sharing Behavior – You had 12 days with 3-4 shares (binge reading days) – Top burst days: – Sept 1, 2008: 4 shares (all security-related articles) – Dec 18 & 24, 2008: 4 shares each (holiday browsing) – Nov 19, 2009: 4 shares (mixed topics)

7. Source-Specific Timing Patterns All major sources showed similar patterns: – Evening preference across all sources (40-45% of shares) – Lifehacker had more late-night shares (18%) than other sources – Security sources (seclists.org) were evenly distributed across time periods

Most Interesting Pattern

Your sharing peaked dramatically in 2009 and then collapsed in 2010-2011. Combined with December 2008 being a huge month, this suggests you were most actively curating and sharing during a specific period of your life (likely 2008-2009) and then largely stopped, possibly when Google Reader began declining or your habits changed.

Me

When did google reader go offline?

Claude

Google Reader was shut down on July 1, 2013. Google announced the closure on March 13, 2013, giving users about four months to export their data.

This timing is very revealing when compared to your sharing patterns:

The Connection

Your sharing activity essentially collapsed before Google Reader was officially shut down:

What Likely Happened

In October 2011, Google removed the sharing functionality built into Reader and replaced it with a Google+ +1 button. This change occurred right when your sharing stopped (2011 had only 2 shares).

So you didn't stop because Reader shut down – you stopped because Google killed the sharing features you were using. The social aspects of Google Reader were removed two years before the service itself ended, which perfectly aligns with your dramatic drop in activity from 2010 to 2011.

Interestingly, one of your starred articles from March 2013 was about Google announcing the Reader shutdown itself, suggesting you were still occasionally checking in even though you'd stopped actively sharing.

Me

Can you validate the links in the shared file? Which ones still work?

Claude

The connection errors suggest the network is restricted. Let me try a different approach by analyzing the URL patterns to give you insights about link viability:Unfortunately, I cannot directly test the URLs due to network restrictions in this environment, but I can provide a comprehensive analysis based on the URL patterns:

Link Viability Analysis

The Bad News: ~85-90% Are Broken

Definitely Broken (108 links – 72.5%): – 103 feed proxy URLs that no longer work: – 16 feedproxy.google.com URLs – 87 feeds.gawker.com, feeds.wired.com, feeds.tuaw.com URLs – 5 dead/restructured sites: – Cult of Mac restructured their URLs – Mobile Boing Boing (m.boingboing.net) is gone – Tumblr blogs may be deleted

Possibly Still Working (23 links – 15.4%):

Unknown Status (18 links – 12.1%):

Why So Many Are Broken

  1. Feed Proxies Died: Google's feedproxy.google.com shut down with Reader
  2. Gawker Bankruptcy: Gawker Media (Lifehacker, Gizmodo) was sold in 2016, URLs restructured
  3. Link Rot: Articles from 2008-2011 are 13-17 years old
  4. Site Redesigns: Most sites have completely restructured their URL patterns

What You Could Try

For the “possibly working” URLs, you could: 1. Try accessing them directly in a browser 2. Use the Internet Archive's Wayback Machine (archive.org) to find archived versions 3. Search for article titles to find if content was republished elsewhere

Would you like me to create a list of just the potentially working URLs, or help you create a strategy for recovering this content via the Wayback Machine?

This is where my conversation with Claude stopped. I did check out the csv file and validated the links through Marked2 manually. Sadly, the robot was correct and majority of the shared links are dead. But there are a few that continue working today and it was interesting to see what I thought was worth my time back then. It was also nice to reclaim some of my digital history and compare that to what I do online today. For example, most of my RSS consumptions these days happens in the AM instead of at night. Of course, this entire exercise was navel gazing of the highest order but it was so simple to do with an LLM that I think it was worth the look back and I appreciate how LLMs made this personal archaeology accessible.