So Claude is a murderbot?
Claude-real-video － any LLM can watch a video
51–60 of 86 posts
Re: Claude-real-video － any LLM can watch a video
#52So Claude is a murderbot?
Re: Claude-real-video － any LLM can watch a video
#53Interesting, but how expensive does it get?
Re: Claude-real-video － any LLM can watch a video
#54my experience with ffmpeg scene detection is that it's flaky. it works, sometimes, but not reliable by any means
Re: Claude-real-video － any LLM can watch a video
#55Cool idea, but keyframes are not videos. Motion, object permanence, are not things Claude can infer from a set of images. Nice demo though!
I have been going through this with claude and qwenvl3:8b this week. Both are pretty decent at inferring context and analyzing contact sheets. Finding high visual interest moments with a mixture of coarse and fine keyframes.
Might be time to check gemma :)
Re: Claude-real-video － any LLM can watch a video
#56Earlier quoted context omitted.
Exactly this. Gemini is best at this. Just give it video link - YouTube works best - and it will analyse the video.
Really, does this work now? What about NotebookLM? I was using it a lot until i realised it was only analysing the transcripts and not the video because i was mostly using it for technical ones with important charts.
NotebookLM still uses the transcript method I think. But Gemini is wonderful. I have been using it to analyze the youtube videos of wrestling matches (trying to build a fan website for WXM, the best pro wrestling promotion to come out of India in a while). It does move by move analysis, audience reaction based match flow tracking, isolates interesting parts of the video (big moves, botches, story beats etc). I have run some experiments to get video editing plans out of it. I think I can combine it with something like remotion skill to make highlight videos.
Edit: BTW, you can analyze about 8 hours a day on free tier.
Re: Claude-real-video － any LLM can watch a video
#57Earlier quoted context omitted.
Identifying objects in pictures was considered an insurmountable task only a few years ago, like in the xckd comic https://xkcd.com/1425/
In the general case, I guess. But watching gauges and dials like battery capacity only take a little work with a deterministic computer vision library.
Or just using voltage pickups like every system that monitors battery voltage ever, or about a dozen other very simple solutions.
Re: Claude-real-video － any LLM can watch a video
#58Cool idea, but keyframes are not videos. Motion, object permanence, are not things Claude can infer from a set of images. Nice demo though!
[flagged]
Re: Claude-real-video － any LLM can watch a video
#59Cool idea, but keyframes are not videos. Motion, object permanence, are not things Claude can infer from a set of images. Nice demo though!
[flagged]