Hacker News Reader

Comment by simonw | Hacker News Reader

The most interesting thing about the Gemini models is still their multi-modal support: they accept audio and video input, OpenAI and Anthropic's flagships are still image-only.

Gemini Flash is also pretty cheap, so it's a great family for performing media analysis, like extracting structured data from images and video.

View on HN

Lost in the news was their update to gemini video analysis yesterday, dramatically cutting tokens (up to 88%!) needed to analyze videos.

https://blog.google/innovation-and-ai/models-and-research/ge...

wow thats actually pretty sick, ty, I could use this in the app im building

Yeah we use it a lot for analysing streams and clipping content. As well as analysing social content that gets put out.

We transcode everything to 480p before we send it to Gemini batch api. Works great

Interesting side note: although Opus is still image-only, you can still drag videos into Claude Code and it doesn't blink an eye; it just strips it down to a series of images to parse.

True multimodal support would be way better, but I have no issues pasting in full screen recordings while QA'ing games and having Claude identify and fix issues in the video.

Agree - I do video editing via Claude Code and it does the job just fine. A lot of my tasks involved frame accurate cutting and to do so it will make a composite image of several consecutive frames in a single image and analyse it that way.

Reply on news.ycombinator.com