So close, yet so far away?

I feel a whiplash effect it seems when ChatGPT amazes me with some esoteric explanation (remember to verify boys and girls), but then gets hung up on what seems like the simplest thing.

I was having a conversation with ChatGPT.  I had supplemental information that was printed out; one two page document and one one page document for the record.  I used Google Drive scan document feature, which I love by the way, and seconds later I had two document scans in my Google Drive.  I downloaded each of them, which consisted of a pdf extenstion file of what looks like a photo scan.  I upload the two files into ChatGPT and … it reports it cannot extract any text from either file.  Complete text extraction fail!

After fumbling about a bit I decided to try opening the document scans in Google Drive, and then I asked Gemini to extract the document scan text.  No problem at all!  I then copied the text into Google Docs, to save for future text reference, and uploaded the google docs to ChatGPT which could then be read and added to the context of that conversation.

I feel like I shouldn’t have to use two frontier models to achieve my goals, and also continue to copy and paste stuff.  I should have asked Gemini to create the Google Doc, and I’ll go back later and 

 

Musings – Prompting, productivity, and context

Prompting, Productivity and Context Finish the following sentence: "Blogging is so ..." and yet here I am. Prompting I've been trying to engage people close to me as to their AI experiences and uses, either professionally or personnally.  I find myself reminding...

read more

Subscribed to One Useful Thing

One Useful Thing is the name of Ethan Mollick's substack newsletter.  Ethan is the Co-Director of the Wharton Generative AI Labs. Wharton Generative AI Labs has lots of good information including a prompt library: https://gail.wharton.upenn.edu/prompt-library/ Check...

read more

“Accumulation of Cognitive Debt”

There's an article published at MIT that studied "Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task https://arxiv.org/abs/2506.08872 This blog post was pitched as a rebuttal of sorts to the MIT study - definitely...

read more

The upside of AI

Positive thoughts? I came across two older items last week that really made me feel good about Artificial Intelligence and some of the good aspects and possibilities.  Like most people grounded in reality, the very impact of AI's disruption on the job front and...

read more

That “aha!” moment – a simple image

I finally committed to the "Plus" ($20 a month) version of ChatGPT and have been finding more and more things to use it for, and trying my best not to use it as lazy google.  Hum de dum and I'm looking at making an AI Policy for TQuist,  as well as provide information...

read more

Alexa, cook me some eggs!

NY Times / AMZN deal Here's an article from The Verge about The New York Times recent deal with Amazon do deliver its “editorial content to a variety of Amazon customer experiences,” I shudder to think how little The Gray Lady is getting paid.  However, I hope the AI...

read more