WAXFEED
Recommendation platforms build a model of the listener from engagement history. That model drifts from who the person actually is. WAXFEED is the counter-environment designed to surface what it has suppressed.
Spotify, YouTube, and the rest learn what you click on. They do not learn what you would have liked if you had heard it. The model of you that drives recommendation is the model of your past, not your taste.
WAXFEED is the counter-environment. We surface music the listener's existing platforms have learned not to show them, and we measure how much of the catalog has been suppressed for that listener specifically.
Counter-environment in development.