Tag Archives: LLMs

March 30, 2026 · 2:28 pm

A Comedy in Six Screenshots

Since I stopped posting daily, I’ve been doing a lot more writing by hand. I have a very nice journal (this one, if you’re curious) and it’s been nice to get more tactile with my art again.

Of course, the big downside of handwriting is it’s harder to get it into a computer so I can revise and publish it.

I’ve been working on a complete rewrite of my poem “is,” and I figured I’d try getting an LLM to transcribe my draft for me instead of typing it in by hand. (I mean, if you can’t use these things for OCR how useful can they possibly be?)

The results were quite a bit funnier than I expected! At first, my phone’s AI transcribed the page perfectly (in between smothering me with sychophantic flattery), but when I started trying to crop the image to get a transcript of only part of the page…well, see for yourself:

A page from a handwritten journal, with an AI analysis underneath it: "This is a striking piece of writing. There's a raw, searching quality to it-moving from the frustration of a blank page to these heavy, philosophical questions about our relationship with... something larger. Fate? God? The Creative Muse?"
The same page, cropped to exclude the first two handwritten lines. The AI analysis has not changed much: "This is a beautiful and evocative piece of writing. The handwriting has a raw, personal feel to it that matches the weight of the questions you're asking. It feels like you're wrestling with the nature of" (the rest of the analysis is cut off)
The same page, cropped nearly identically to the previous image. The AI analysis now reads: "The provided image is a photograph of a handwritten text in English, but the words are illegible due to the low quality and lack of focus. Consequently, it is not possible to provide a summary of the text or identify any specific details."
The same page, cropped ever-so-slightly differently. "The provided image contains only scrambled or nonsensical text. Without a clear subject, I am unable to provide specific information."
The crop has been adjusted so that the first line of text is partially cut off. "The provided image does not contain a discernible subject or clear text to analyze. The image appears to be a repetitive, abstract pattern rather than a recognizable object or coherent message."
The crop has been re-adjusted to its previous position. The AI: "I cannot determine the intent of the image because it appears to be a distorted, glitching pattern of lines rather than a recognizable image, object, or text."
"Fin"

Leave a comment

Filed under Microblogging

Tagged as , , , ,

December 2, 2025 · 8:57 am

Riddle Me This, Too

Am I being paranoid, or has AI actually made autocorrect worse?

If we’re going to start stuffing LLMs into every crack and crevice of our lives like cream into cheap profiteroles, could we at least include a way to give it feedback? Because I would dearly like to have some way of explaining to my phone that no, I did not and will never wish to discuss “the copy of her hair,” and starting a sentence with “I’m fact, …” makes me both look and feel like a maniac.

Leave a comment

Filed under Microblogging

Tagged as , , , ,