Internet Archive Artifact #000

Estimated Reading Time: 5 minutes

Welcome to this new series where I explore random artifacts from one of my favorite places on the Internet, the Internet Archive.  Its biggest claim to fame is the Wayback Machine, where you can look at what a website looked like at some point in the past.  So you could go look at what the USA.gov website looked like in December, 1999 or see what this blog looked like in 2015!  But the amount of artifacts deeply stored within the Internet Archive is endless!

Why do this?

Well, I'm a big fan of the public domain and open access.  I wrote an entire dissertation about making things more widely available and I spend a good part of January the last few years putting up new public domain films on my YouTube channel, which includes having to submit appeals to YouTube because companies are still claiming copyright. I like the idea of reminding folks of what's already out there to play with.

I also needed a new challenge or focus for this blog. Something that keeps me coming back to share, think, and explore about things that aren't about AI!

  

Another thing that inspired this new series is that I like the Internet Archive but exploring it can be a challenge.  There's a lot of content, and it's not easy to find thing or rather find things at random.  I feel like I have to dig in and that feels a little less serendipitous for how I might like to engage with it.  With the help of AI, I built a small web program that would send me to a random detail page on the Internet Archive. 

Once I had a mechanism for random encounters, I realize that this would be a fun series for me to blog about.  One thing I've missed about blogging that was hard to do with the dissertation was committing to some longer term project.  Now, with that out of the way, I feel like I can pursue something like this more consistently.  And thought I'd like to commit to it as a 365 project like I have done with short stories and photos (while having good starts and failing with others, such as my poem a day), I'm hoping that I can do this one on a weekly basis.

So what can you expect?  Well, I think the format will be pretty straightforward.  I'll share what I was sent to, what sense I could make out of it (sometimes with the help of AI, particularly if it's in another language), and what are my thoughts about encountering such an artifact.  I hope it provides enough strange and curious things to keep readers interested and even if it doesn't, I'm sure I'll enjoy it.  

Screenshot of the browser extension

You can do it too!

And, of course, I encourage folks at home to play along.  If it's useful, here is the prompt that I used with Claude to get the app that I have:  

My prompt:

"I want to build a browser extension that will randomly pull a resources from the depths of the internet archive.  I would like some features to put parameters around it (e.g. image, sound, video, software, book, newspaper, etc and when the item is from and other tagged features)...interview me to get more details about how the extension should look and feel... also, I have no real coding skills so also help me build the best extension in the cleanest code possible"

Claude's response (Note: I have my Claude personalized so that it asks questions--see this post for more insight):

"How do you envision triggering and viewing random finds?

1. Popup window. Click the extension icon, see a random item preview in a small overlay, click through to the Archive if interested.
2. New tab experience. Each activation opens a full new tab with the random resource, more immersive and visual.
3. Browser sidebar. A persistent or toggleable panel that refreshes with new items, allowing browsing while you work.
4. New tab replacement. Every time you open a blank new tab, it shows a random Archive item instead of your default page.
5. Hybrid (1+3). Popup for quick discovery, with an option to pin it as a sidebar for longer exploration sessions.

Question 2: Filter Persistence and Complexity

How should the filtering system behave?

6. Set-and-forget profiles. Create named filter profiles (e.g., "1920s newspapers," "80s software") and switch between them.
7. Quick toggles. Simple on/off buttons for major categories visible in the interface, adjusted on the fly.
8. Advanced query builder. A more powerful interface letting you combine media type, date range, collection, language, and other Archive metadata fields.
9. Randomize the randomness. Minimal filtering. You want maximum surprise, with perhaps only a single broad category toggle.
10. Hybrid (6+8). Saved profiles for frequent use, but with access to an advanced mode when you want precision.

Question 3: Visual and Emotional Tone

What aesthetic should the extension convey?

11. Retro/archival. Sepia tones, typewriter fonts, aged paper textures. Feels like opening a dusty box in an attic.
12. Clean minimalist. White space, modern sans-serif, the content is the star. Think museum gallery.
13. Playful/whimsical. Bright colors, animations, a slot-machine or "spin the wheel" energy for the randomization.
14. Dark mode scholarly. Muted dark interface, subtle accents, feels like a research tool for late-night exploration.
15. Hybrid (11+14). Retro visual elements but in a dark, muted palette. Scholarly nostalgia."

My response was:  "2 7, 8, 9 11"

It asked me a few more questions, and again, I chose selections.  The whole interaction took less than 3 minutes back and forth.  I did other tasks as it built the actual program.  The result is a Chrome browser extension which executes whenever I open a new tab, it presents the Archive Roulette and shares something new.  

---

Did you enjoy this read? Let me know your thoughts down below or feel free to browse around and check out some of my other posts!. You might also want to keep up to date with my blog by signing up for them via email.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.