After 115K videos in prod, engineer shares Gemini video-understanding gotchas and hacks
TheMoonMidas · x · 2026-09-07
Engineer karolzdeb shared hard-won lessons from running 115K videos through Gemini in production:
- Default 1fps sampling misses details, especially motion; the team uses 10fps, but costs scale linearly with frame rate.
- Videos are downscaled to 480p, so feeding higher-resolution video yields no quality gain.
- Quality hack: send high-resolution screenshots alongside the video file — effective but expensive fast.
- Scene-boundary detection has a dedicated recommended approach (detailed in the original thread).
TheMoonMidas resurfaced the thread with those caveats.
More from coding & agent
- Zero critical vulnerabilities found across 120 Replit-built apps, CEO weighs in — amasad · 2026-09-07
- Ghost now auto-deploys agents to fix issues they discover — BLUECOW009 · 2026-09-07
- Unverified: claims of using 'GPT-6-ASTRA' inside Claude Code — BLUECOW009 · 2026-09-07
- One week with Grok Bot running 5 businesses: the chores an autonomous agent actually absorbed — PrajwalTomar_ · 2026-09-07
- Fully automated product demo videos: local LLMs, 34 episodes, zero human editing — Ok_Cartographer_6086 · 2026-09-07
- Skip the middleware: wire two AI CLIs together with plain tmux — viksit · 2026-09-07