ASCII art by chatbot
I've finally found it: a use for chatGPT that I find genuinely entertaining. I enjoy its ASCII art.
(huge thanks to mastodon user blackle mori for the inspiration)
I think chatGPT's ASCII art is great. And so does chatGPT.
Lest you think chatGPT (here, the March 14 2023 version) is alone in its high ratio of confidence to skill, I also got Bing chat (which uses GPT-4) and Google's Bard to generate some ASCII art.
Bing:
Bard:
It's not that the ASCII art has nothing to do with what I ask for. There is often an attempt. Followed by a wildly optimistic rating.
Asking for clarifying refinements to the design usually leads to surprising places.
This unicorn's horn, for example.
Or this long jumper's fingers.
I've never seen a rating below 7/10, and any change I suggest to the art causes the chatbots to raise their ratings and praise their artwork even more enthusastically. (The exception is if I ask for a change to a drawing that has already been rated a 10/10; then I get a 9.5/10).
I do like Bard's giraffes. I would also give them a 9/10, but for different reasons than those Bard cites.
What's going on here? The chatbots are flailing. Their ASCII art is terrible, and their ratings are based on the way ratings should sound, not based on any capacity to judge the art quality.
Am I entertained? Okay, yes, fine. But it also goes to show how internet-trained chatbots are using common patterns rather than reality. No wonder they're lousy at playing search engine.