Opus 5.5 is good at explainer videos
- ID
- 28487
- Status
- summarized
- Published
- 25 Sep 2026, 4:28 AM
- Fetched
- 25 Sep 2026, 6:46 PM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://launchvideo.io/
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.0
- Created
- 25 Sep 2026, 6:47 PM
- Tags
- Audience
- developersvibe_codersai_agent_userssaas_founders
What happened
LaunchVideo is a Hacker News demo that turns a URL or one-line prompt into a 30-second 1080p launch video by having Claude Opus 5.5 write the whole film as HTML, then rendering it in a fresh microVM. The write-up is unusually concrete: one TypeScript agent file with three tools (web_fetch, check_scene, render_video), roughly 90k input + 15k output tokens per film, about four minutes per job in an Amazon Linux 2023 arm64 VM with 4 vCPU and 8 GB RAM, discarded afterwards. There is no video model — requestAnimationFrame, timers, Date, and CSS/Web Animations are replaced with a virtual clock so each frame is a deterministic seek, then 1920x1080 at 30 fps JPEG frames are piped into libx264 at crf 18.
Why it matters
If you build agent-generated media, the reusable pieces here are the virtual-clock trick (deterministic frame seeking instead of a diffusion video model) and the secret-handling pattern: the form mints a Vercel Blob token scoped to one path for three hours, parked in a per-job manifest and fetched by job id, so the agent holds no credentials. Budget the cost before copying it — ~100k tokens per 30-second video means per-clip cost scales with Opus-tier input pricing, and the first tool call spends about a minute installing Playwright's headless Chromium and a static ffmpeg inside a VM you then throw away, which is a large fixed overhead on short clips.
Discussion angle
The 271-point thread is worth mining for the counterargument: is 'LLM writes HTML, virtual clock renders frames' a genuinely better architecture than a video model, or just a cheaper way to make slideshow-grade output? Compare the ~100k tokens and ~1 minute of Chromium/ffmpeg install per clip against a hosted video API on cost and turnaround.