aiweirdness.com/post/188342947…
aiweirdness.com/post/166814009…
But @susanthesquark of @nytimes arranged for a Professional Illustrator & Jessia Ma nailed it:
nytimes.com/interactive/20…
This is most obvious here. It grabbed words like bitcoin & titmouse that weren't in the example costumes. Compare to 2017 (conchpaper??)
In 2017/2018 that meant more nonsense words.
The 2019 neural net reverts to its internet training data, introducing more Game of Thrones, Frozen, and racism. Oh, internet.
Unfiltered text from 2017 char-rnn vs 2019 GPT-2, both trained on the same dataset of halloween costumes & sampled at chaotic 1.4 temperature.
reverting to nonsense vs to celebrity references