Latest experiments reveal AI is still terrible at naming paint colors
Or maybe Janelle Shane's neural network is secretly making fun of
humanity?
Several weeks ago, artist and coder Janelle Shane tried to train a neural network to name paint colors. The results were…not good. “Stanky Bean” was a kind of dull pink, and “Stoner Blue” was gray. Then there were the three shades of brown known as “Dope,” “Burble Simp,” and “Turdly.”
These results were so bad that they turned the corner into delightful hilarity, and Shane’s blog postabout them went viral. Almost immediately, AI coders started offering tips on how she could tweak the algorithm to get better results. So Shane dutifully went back to the virtual drawing board, adjusted the AI’s creativity levels, and gave it some new datasets. The results were…well, you decide.
First, Shane realized that part of the initial problem was that she’d cranked up the neural net’s “temperature” variable, which meant that it was picking less likely (or “more creative”) possibilities as it generated paint names letter-by-letter. So she turned the temperature variable down, and found that the names were still pretty silly but they at least matched the colors most of the time. Plus, the colors themselves seemed more varied:
