Lichtung
林间空地A working prototype built to illustrate how three distinct mechanisms behind perceived polarization might be targeted at the system level — through algorithmic ranking, information presentation, and identity-data surfacing.
10-minute walkthrough ·English subtitles
Open the live demo →I built Lichtung to make these interventions experimentally testable. In my PhD, my next step is twofold: to test their causal effects in feed environments, and to translate the underlying intervention functions into conversational AI as a second test arena.
No signup, no configuration — the feed loads running.
Please note
This is an early-stage demonstration prototype, not a study. None of the three interventions has been tested in a controlled experiment, and nothing in this video reports an effect on perceived polarization. The demo exists to make the design logic inspectable. Testing is the next step: an RCT in a high-fidelity feed simulator.
About the data · Polling distributions are from published public sources, cited on screen. News items are real headlines and links. All user profiles and comments are synthetic.
Built
React + TypeScript. The ranking layer, distribution component, and identity layer are implemented from scratch. github.com/rfb4c/Lichtung ↗