Ever since Google released the neural network DeepDream in 2015, we've learned that AI is capable of creating things that are far trippier (and far more alarming) than anything the human mind can dream up. Filtering videos like scenes from Fear and Loathing in Las Vegas (1998) through a neural network can have some truly disturbing results, as the computer reaches to find meaning and shapes where there aren't any. The results are a colorful collage of mashing limbs, teeth, and animals that rotate and transform as the video rolls. In other words, the worst thing we've ever seen.

Even a video as relaxing as an episode of Bob Ross's The Joy of Painting can't escape unscathed. Along with the nightmare kaleidoscope of eyes and dog faces, the audio is warped and strangely quiet. Watch the video at your own risk—it gets pretty unnerving.

[h/t SPLOID]