Whatup doomers it’s ya boy TL;DR Geodesic finds mildly positive results from the first-pass experiment testing Turntrout’s proposed self-fulfilling misalignment hypothesis. The experimental question is approximately: Can we avoid the model internalizing silicon racism? Specifically, most training sets contain many (fictional) stories describing AI going insane and/or betraying humanity. Instead...
Meme-Magick v1 Hi, I'm Aaron. You may know me from some projects, most recently among them Hyperstition AI. It's done. Here's five thousand AI-generated novels. Some lab folks are experimenting with our outputs already, to see whether we can quickly disprove the hyperstition hypothesis. If you're so inclined, you're invited...
Epistemic status: Subjective report describing youthful exuberance. The actual experimentation part of this was very badly executed. In light of the recent homemade peptide vaccine, this is a writeup of my experiences in insufflating internet chemicals. This happened during a period of my life when I was very bored, kinda...