GPS: Goblin’s Perfect Sense (but in the phone)

Aurora Borealis? At this time of year! At this time of day! In this part of the country! Localized entirely within eastern Colorado?

Yes, the box that contains “Shirt”

Fun fact, the geographic center of the contiguous states is very near the center of the top edge of Kansas. Including Hawaii and Alaksa, the geopraphic center shifts to the top left corner of South Dakota, just east of where Montana and Wyoming meet.

As someone who lived in Kansas, just look for the middle of the middle.

The center column of states has 6 states (North Dakota, South Dakota, Nebraska, Kansas, Oklahoma, Texas), and Kansas is in the middle of that vertical line (given that the northern 3 are a bit thinner).

Something something surface tension of blood :P

Smalbut!

Tau-nay

Meanwhile, the dbzer0 version has an eyepatch and says “Respect no Copyright”

So you generate a completely random grid of pixels. Tell bot 1 to unblur it, then bot 2 evaluates how much it resembles the prompts, then bot 1 takes that evaluation and uses it to unblur the image a bit better, bot 2 evaluates again, and so on and so on until you have an image that passes evaluation. So bot 1 has never even been trained on other peopes data.

I’m sorry, I’m not understanding. So Bot 1 relies on Bot 2 to evaluate Bot 1’s iterative images. Is Bot 2 not trained on the Mona Lisa in order to determine if the image resembles the Mona Lisa? And if Bot 2 has no idea what the Mona Lisa or its artist’s works look like, can it reliably guide Bot 1 through turning blurs into an image that resembles the Mona Lisa?

…did you hear Steve Jobs died to figma?

(Sorry I had to)

Me when I have to learn any new OS or programming language.