The Aisle "the moat is the system, not the model" blog post comparing Mythos' results to their system's was misleading, and seemed to be an attempt to ride the coattails of attention on Mythos. It was of low enough quality that I'd want to see more details of exactly how these vulnerabilities were found.
From what I see the code downsamples video to 5 fps, so 1 hour of video is 3600 seconds * 5 fps = 18,000 frames. 18,000 frames * $0.00079/frame = $14.22. A couple dollars more with the overlap.
(The code also tries to skip "still" frames, but if your video is dynamic you're looking at the cost above.)
you're right that the code uses ffmpeg to downsample the chunks to 5fps before sending them, but that's only a local/bandwidth optimization, not what the api actually processes.
regardless of the file's frame rate, the gemini api natively extracts and tokenizes exactly 1 fps. the 5 fps downscaling just keeps the payload sizes small so the api requests are fast and don't timeout.
i'll update the readme to make this more clear. thanks for bringing this up.
Fair, I was fine going this direction because you're a click a way from get the full view and with the hover there isn't much more "preview" to show. My number one priority with the hover was making it obvious the given thumb is interactive.
Or one person types 76 pages. This is a thing people used to do, not all that infrequently. Or maybe you have one friend who will help–cool, you just cut the time in half.
Typing 76 pages is easy when it's words in a language you understand. WPM is going to be incredibly slow when you actually have to read every character. On top of that, no spaces and no spellcheck so hopefully you didn't miss a character.
It's happening again. Spoofing is in progress, rendering another image. ADS-B Exchange has blocked access to the ICAOs/hexes in question--if you try to look at their history you get redirected to the base map.
reply