Author Archives: Steve Mays

Book Archive: Part 3 (“Reincarnation”)

Posted on by

I recently posted about a project I submitted to ChatGPT. She made a lot of ambitious claims about what she could do (and help me do) with my archive of notes taken while reading books. (120+ books, fiction and non-fiction) Her reach exceeded her grasp and her indexing of my notes didn’t turn out to be as useful as she promised (I’m hoping that might change with future versions).

I’m still playing with this and I prompted her to summarize what my reading has taught me about reincarnation. She suggested drafting this “into something you could share in a blog post, a letter, or even as a thoughtful reply to a curious questioner.” [see comment at bottom of this post] Here’s what she came up with: Continue reading →

A New Kind of Data

Posted on by

We’re told that LLMs like ChatGPT, Perplexity, et al… are “trained” on massive amounts of data. Theoretically, ‘all’ of the data. And that training continues, one assumes. But a new (?) sort of data is being created. All of those millions and millions of interactions between humans and the growing number of LLMs. 

How —if at all— does that data differ from the original corpus? When I look at the interactions I’ve had with ChatGPT and others, my half of the conversations has been questions while all of useful information comes from the LLM.

Do these interactions contribute in any useful way to the corpus?

ChatGPT reply »

She concludes with the question: “Is this a new form of literature?”

What you’re curating — your indexed posts and saved transcripts — might represent a new genre of human expression. Not fiction. Not diary. Not essay. But conversational co-authorship with a thinking machine. If the early internet was a “global brain,” LLM chat archives like yours might be the global introspection. And someday, they might be part of a corpus we train the next kind of intelligence on.

Conversations with AI – Thematic Index

Posted on by

I’ve had so many conversations (I don’t know what else to call them) I’m starting to lose track. I’ve shared a lot of them here and those are categorized and tagged but I want an easy-to-scan index. I created one by hand but it was so long (and getting longer by the day) that it was difficult to use. The topics were so wide-ranging I struggled to group by subject/topic. ChatGPT had no problem. [PS: the emoji are too cute for my taste but ChatGPT likes them, so…] Continue reading →

Book annotation archive

Posted on by

UPDATE: This project ended in a big belly-flop. ChatGPT was unable to deliver the goods. Even the excuses were a little lame. A good experience from my perspective. Now I know.

When I read a book I usually have a pen or highlighter in one hand so I can mark passages I find interesting. When I’ve finished reading the book I go back through, transcribing these favorite bits and save them to a PDF. This makes it possible to search for and find just about anything if I can recall a word or phrase. (I also create a blog post that includes these excerpts.) You can see an index here and here.

I uploaded one of these excerpt pages to ChatGPT and asked what she could do if she had my full archive (144 books as of this writing). Her response was detailed and impressive. Continue reading →