No video model: Claude coded a startup launch video in 1min for ~$2 with JS, Playwright, ffmpeg
deedydas · x · 2026-09-24
Deedy clarifies his inference startup's launch video used no video generation model and no extra libraries — just JavaScript, Playwright and ffmpeg, with Claude coding the website animation and recording it. Total: 1 minute of video for $2, versus weeks/months and 1000x the cost via agencies. He argues humans prefer video over text, changing the substrate of technical communication.
Related event: Opus 5.5 Builds a Startup Launch Video in One Minute for About $2(3 posts)→
More from coding & agent
- User automates entire video clipping workflow with Nous Research's Hermes agent — Teknium · 2026-11-12
- As models improve, writing good evals gets harder and more important — amankhan · 2026-11-12
- Free AI game jam in SF Nov 14–15 with teams from Anthropic, Google, Meshy, OpenAI — chrisfirst · 2026-11-12
- Omarchy 4.6 lets you share local AI models across your tailnet, says DHH — alexcovo_eth · 2026-11-12
- Coding harnesses hand shell access to inference providers — 4-step gateway mitigation — shensi · 2026-11-12
- Slack's David Hoang: agents beat people on coordination, proposes 'boundary agents' — davidhoang · 2026-11-12