Docs / source reviewed
CrowdCut
Let audience suggestions steer the next video scene
How this project uses Jev
- Input
- Viewer comments, current scene context and existing proposed story actions
- Jev decides
- Assess whether a comment is actionable and suitable for public display, then match it to an existing idea or a new one
- Code executes
- Server code aggregates directions, requests the next video from Hedra and maintains a shared playback timeline
Evidence and limitations
Jev classifies comments; Hedra generates video. A labeled simulation fallback without a key is not real Jev inference. Rendering can lag playback and has no automatic spending cap; closing a viewer tab does not stop generation. No video generation or live-playback test was performed here.
This project has not been run independently here. Author-reported results are not independently verified results.
Original sources
- https://github.com/lostviolinist/crowdcut-jev-hedra/blob/81f4056f0dbc5ccab059118154cec186e46c9397/README.md ↗
- https://github.com/lostviolinist/crowdcut-jev-hedra/blob/81f4056f0dbc5ccab059118154cec186e46c9397/lib/jev.ts ↗
- https://github.com/lostviolinist/crowdcut-jev-hedra/blob/81f4056f0dbc5ccab059118154cec186e46c9397/lib/live-state.ts ↗
- https://github.com/lostviolinist/crowdcut-jev-hedra/blob/81f4056f0dbc5ccab059118154cec186e46c9397/app/api/live/comments/route.ts ↗