Make 370 Hours of Video Searchable for Just $10 in GPU Time
vanstriendaniel · x · 2026-07-31
A developer demonstrated how to turn massive video archives into searchable databases using AI. By processing 1,864 public-domain films from the Prelinger Archives, cutting them into 60-second chunks, and running an open-source 2B video model for multimodal feature extraction.
The entire index cost only about $10 in GPU compute. Users can now search with natural language queries (e.g., "typing on a computer keyboard") and jump directly to the exact moment the action occurs on screen.
Related event: AI Makes 370 Hours of Public Domain Films Searchable for $10(3 posts)→
More from coding & agent
- Connected steps are not a workflow: nobody designs the handoff — usehive · 2026-10-16
- Making Blender animations with Opus, Astra and Argon: how you prompt still matters — chongdashu · 2026-10-16
- Running PolyStrata + Cline coding agent on a $0-fancy laptop at ~90 tok/s — rpwoerk · 2026-10-16
- How do you attribute agent gains: model training or infrastructure? — jrxna · 2026-10-16
- Feed Claude your books, blogs and top engineers' code for claude.md — 'it now writes better code than me' — blaizedsouza · 2026-10-16
- Open-source /label plugin auto-names and colors Claude Code sessions in one step — hermanschutte · 2026-10-16