Discussion about this post

User's avatar
SDG Morgan's avatar

The comments here made me think of this wonderful passage from Wendell Berry that my pastor recently cited, where Berry talks about why he resisted using a computer to write his books.

“ a computer, I am told, offers a kind of help that you can’t get from other humans; a computer will help you to write faster, easier, and more. Do I, then, want to write faster, easier, and more? No. My standards are not speed, ease, and quantity. I have already left behind too much evidence that, writing with a pencil, I have written too fast, too easily, and too much. I would like to be a better writer, and for that I need help from other humans, not a machine.”

Expand full comment
Tyson Cadenhead's avatar

It's funny because after reading this, while I noticed many of the same things as my beautiful wife, Heather, it actually led me to the opposite belief -- that the 1st version was AI and the second wasn't.

As a computer programmer and software engineering manager, I've spent a lot of time working with various AI models, which I think has given me a lot of insight into the "tells" of most LLMs.

The most obvious thing I would look for is moralizing to put a bow on a story. Most LLMs are trained to want to find a lesson. I suspect it's because many of them are trained on articles and blog posts on the internet that have a tendency to end on an uplifting note.

AI also doesn't tend to be comfortable with unfinished thoughts or open ended imagery. For example, why did his secretary insist there were no first class options? Why couldn't he have coffee before take off? Why was he annoyed by a woman pulling a scarf over her head? I don't think AI would leave any of that nuance.

Expand full comment
26 more comments...

No posts