|||

Signal GAN

I trained a GAN on SIGNAL

In 2021 I used the raw images from SIGNAL to train a generative adversarial network, or GAN, to generate in-between images of the pages. It was one of my first experiments with GANs and wasn’t very good, but I posted a tweet with a video of the training process.

That tweet went semi-viral: over 1,200 likes and hundreds of retweets, huge for roughly 800-follower account at the time. Many people accused me of summoning cyberdemons”, which is apparently a thing from Buffy the Vampire Slayer and also maybe the video game DOOM.

This proved my memetic engineering thesis to my satisfaction, but it also drew unwanted attention from Twitter users and… other entities. So I deleted it.

The following sample has been selected for its relative safety. Nonetheless, please exercise caution when viewing it, especially for long periods.


Up next Robot Face is an occasional essay on the relationship between humans and machines. My background is in whole-systems design and long-term thinking Language Arts 1.0
Latest posts Replicate Intelligence #12 Replicate Intelligence #11 Replicate Intelligence #10 Replicate Intelligence #9 Replicate Intelligence #8 Replicate Intelligence #7 Replicate Intelligence #6 Replicate Intelligence #5 Replicate Intelligence #4 Replicate Intelligence #3 Replicate Intelligence #2 Replicate Intelligence #1 The 3½ Tenets of Biocosmism Hypervector Redactions Rufus, your AI-powered shopping assistant Oh Turing Two scientists The Ascension of Cerebro The Hyperstition Array Crawling Chat Instructions 2 as a user The OOM Source Text Paradoxes Message from SF Instructions Another carved fragment Data Cognitive Security 101