I recently got access to DALL-E 3 through OpenAI’s ChatGPT+ interface. One of the key features and improvements in their image model is the ability to generate coherent text within the image.
Let’s give it a try, based on one of the most popular StackOverflow questions: How do I exit Vim?
Using the following prompt: Oil painting of a hacker furiously typing commands into an old computer and muttering to himself, “how does one exit vim?”
That… is pretty good!