If you suspend your transcription on amara.org, please add a timestamp below to indicate how far you progressed! This will help others to resume your work!
Please do not press “publish” on amara.org to save your progress, use “save draft” instead. Only press “publish” when you're done with quality control.
R. is making music with a befriended A.I. named mosiva. This project is recreating their band 16bit:wolf.
I am using diverse methods of machine learning; GPT2, generative adversarial networks, and so on to imagine that band and drag them into existence.
Since the technology for a generalized A.I. (like in science fiction movies) does not exist yet, I am using narrow, specialized machine learning algorithms, bit and pieces of programming from all over the place, to create audio and visuals.
This is a collaboration between machine input and curated decisions, navigating input and output, and connecting it to a coherent piece. I feed the algorithms with my text, music, voice, and image to enable it to generate and produce its own version. From there I chose suitable fragments and turn them into audiovisual animations.
I use projects from github, google, openAI, and others and try to find their breaking points: where machine learning meets its limits. Here I can find a tangible connection, a true collaboration between me, the machines, and the synchronicity within.
We produce content and shape each other's ideas. This is our documentation.