It then gave me step-by-step text instructions on how to use the OCR feature in Microsoft Word to import text from a picture, and admitted in step 3 that the function doesn't exist. There were 6 steps.
My first prompt was just, "Give me some attempts at an image that is inspired by my Lemmy username: EnterOne," (keep in mind, this is not the prompt ChatGPT gives to DALL-E) which gave me some cool results like this:
But I wanted one that was informed by my username's origin, so I explained the source material to it in detail, and asked it to create something. The first results were a little too on the nose, so I asked it to be more covert and artistic in referencing the source material. All in all, I went through about 20 iterations, because DALL-E was having a hell of a time spelling my username while keeping close to a style I liked.
I never could get it to produce this with text over it
Wasn't Inky the driver?
That's insightful, thanks. Not knowing the subtleties of it, I imagined they would just need to make sure the thing has an IR receiver and is programmable, which they can test with whatever remotes and associated devices they have around. Then I could program the finished thing with my remote at home.
Hey, wow this blew up! I should turn notifications on. I want a programmable IR volume knob. Just a big, chunky knob to set on the table or couch to control my home theater receiver. No Bluetooth or Wifi or zigbee or anything like that. That's all.
Oh, look. Richmond's still alive.
Or, "An Armadillo Eating a Mountain"
Remember to douse your campfire until it's cool to the touch before you leave. Only you can prevent forest nebulae.
Do I hate the answer-my-own-question format of explaining things? Passionately
That is my experience, as well. That's not workable, since it would take an extremely long time to change the volume by a meaningful amount. I guess I'll need to keep my receiver remote out for volume control.
ChatGPT takes the liberty of creating a DALL-E prompt that it doesn't feel the need to share with the user. You can, however, ask ChatGPT to share the exact prompt and seed with you to reproduce the image. Here is the actual prompt and seed DALL-E ended up working with:
Prompt: "A step-by-step visual guide on using Optical Character Recognition (OCR) in Microsoft Word. The guide includes steps like opening Microsoft Word, inserting an image into a Word document, selecting the image, and using the OCR feature to convert the text in the image into editable text. The layout should be clear and easy to follow, with each step labeled and illustrated in a user-friendly manner, catering to users with basic proficiency in Microsoft Word."
Seed: 3993182816
To be clear, ChatGPT decided on its own to create and send this prompt to DALL-E in response to my request for tech support.