It was definitely making use of the content, and not just my prompt.
…
Ok, being simplistic about the actual workings: anything a LLM outputs is based only in the training data or the prompt, a LLM does not “create” anything.
I really doubt your blog is statistically significant enough represented in the training data, therefore I can only assume that yes, your blog post URL referenced was web scrapped by ChatGPT and, and any other URLs linked by this main URL that the scrapped deemed significant to the prompt, and all that text was in fact added to the full internal prompt that was processed by the actual LLM.
Just as a referenced for “second brain” local apps I suggest to look at dendron. Dendron is no longer being maintained but it still works and I use it for my notes since I adopted it a few year ago, it’s pretty great for programmers since it works on top of VS Code.