Image 01 Image 03

‘Stanky Bean’ and Other Hilarious Paint Colors Invented by an AI

‘Stanky Bean’ and Other Hilarious Paint Colors Invented by an AI

‘Stoner Blue’ looks nice

Should we go with the Sindis Poop or the Burple Simp?

A programmer fed a neural network more than 7,000 Sherwin Williams paint color names, testing the algorithm to see what paint names it colors it would produce. The results are hilarious:

So it turns out you can train a neural network to generate paint colors if you give it a list of 7,700 Sherwin-Williams paint colors as input. How a neural network basically works is it looks at a set of data – in this case, a long list of Sherwin-Williams paint color names and RGB (red, green, blue) numbers that represent the color – and it tries to form its own rules about how to generate more data like it.

Last time I reported results that were, well… mixed. The neural network produced colors, all right, but it hadn’t gotten the hang of producing appealing names to go with them – instead producing names like Rose Hork, Stanky Bean, and Turdly. It also had trouble matching names to colors, and would often produce an “Ice Gray” that was a mustard yellow, for example, or a “Ferry Purple” that was decidedly brown.

These were not great names.

The entire post is worth the read. I think it’s safe to say we don’t have to worry about an uprising of robot overlords anytime soon.

Follow Kemberlee on Twitter @kemberleekaye


Donations tax deductible
to the full extent allowed by law.



Nothing to fear from neural nets. They’re highly constrained to a specific problem domain for which they’ve been programmed, and they have to be “trained” with reams of data before they can accomplish anything. They’ll never “think” on their own. They’re really just sophisticated pattern recognition algorithms.

Some could have been 60’s band names.

Or what some were ingesting.

Was this the same computer algorithm that has been predicting we’re all gonna’ die from global warming?