No framework needed: model extracts cursor pixel-by-pixel, getting bitter-lessoned
nickbaumann_ · x · 2026-10-29
Developer nickbaumann asked Astra to extract the cursor from a Screen Studio video. Instead of using remotion, hyperframes, or ffmpeg, the model diffed each frame against a clean frame pixel-by-pixel, turning changed pixels into a transparency mask to lift out the cursor and click effects. His takeaway: just ask for outrageous things and the model figures it out—frameworks are getting bitter-lessoned.
More from coding & agent
- Video2Game: H3 Max Generates Gameplay Video, Claude Turns It Into a Playable three.js Game — OdinLovis · 2026-10-29
- After 3 Years of Heavy AI Prompting, Domain Vocabulary Beats Prompt Tricks — Dimillian · 2026-10-29
- Agents push compute back to CPUs: $221B server CPU market seen by 2030 — BenBajarin · 2026-10-29
- Cursor removes its beloved Cmd+K command, frustrating power users — jbhuang0604 · 2026-10-29
- Designing a skill like an app: a developer's iteration diary for interface-bts — round · 2026-10-29
- One prompt one-shots a walkable 3D ship where AI agents visibly work around the clock — InternationalGap3698 · 2026-10-29