Guessing Amazon image URLs using GitHub Copilot#

I was experimenting with the new Readwise export API and it gave me back the following JSON:

1
{
2
  "user_book_id": 15433610,
3
  "title": "Screenwriting: The Sequence Approach",
4
  "author": "Paul Joseph Gulino",
5
  "readable_title": "Screenwriting",
6
  "source": "kindle",
7
  "cover_image_url": "https://images-na.ssl-images-amazon.com/images/I/51UMeAAJNRL._SL75_.jpg",
8
  "unique_url": null,
9
  "book_tags": [],
10
  "category": "books",
11
  "readwise_url": "https://readwise.io/bookreview/15433610",
12
  "source_url": null,
13
  "asin": "B00F9476Y0",
14
  "highlights": []
15
}

The image URL https://images-na.ssl-images-amazon.com/images/I/51UMeAAJNRL._SL75_.jpg produced a tiny little image - this one:

I wanted to get back a bigger version of that image. On a hunch, I popped open a VS Code window running GitHub Copilot and typed this:

1
https://images-na.ssl-images-amazon.com/images/I/51UMeAAJNRL._SL75_.jpg
2
# That image but bigger:

It autocompleted for me:

1
https://images-na.ssl-images-amazon.com/images/I/51UMeAAJNRL.jpg

Which is indeed a larger version of the image!

Screenwriting: The Sequence Approach - a much bigger book cover image, with legible text

I typed # and hit autocomplete again, to see what would happen, and got this:

1
# That image but smaller:
2
https://images-na.ssl-images-amazon.com/images/I/51UMeAAJNRL._SL50_.jpg

Another correct guess. GPT-3/Copilot clearly includes training data that has seen these URLs before.

I typed # one more time and it autocompleted again to:

1
# That image but with a different format:
2
https://images-na.ssl-images-amazon.com/images/I/51UMeAAJNRL._SL50_.gif

… and this time that URL is a 404. Copilot made this one up!

Here’s the full flow in VS Code:

Animation showing the above prompts being executed in VS Code