Live data from Hacker News

$100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

tryai.dev

131–140 of 581 posts

Re: $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

#132

No need to take any pot shots at this trash in terms of aesthetic efficacy in earnest, if y'all know what I mean. But as an experiment, it's interesting. There seems to be an odd consistency to all of them, which reveals a kind of internal logic & coherence of sorts that courses throughout any iteration. Aesthetically, where can you place these? I feel like the late David Lynch could have used some tropes in his unne…

> I did crack up seeing a martini glass presented to the camera, then float in place on it's own

It's just a cheap video-generation model doing its thing. I wonder if the orchestrator model noticed this and tried "Create a scene with a martini glass. Make no mistakes".

Re: $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

#134
The results are pretty bad for a top stars music video. But it's pretty impressive for not very important short clips like insert shorts of cheap Ads.

I'm scared because that's the most labor intensive area. Top talents will survive but all the volume industry will collapse.

Re: $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

#135

This is how you do AI music videos: https://www.youtube.com/watch?v=Njk2YAgNMnE Lean into the not-quite-but-almost uncanny-valley-ness. Make it a feature, not a bug.

[flagged]

Nah, us fiends watch things like https://youtu.be/TuGg0aMO1NI?is=zFRpAeel1keKFbsb

Re: $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

#136
post #93

Earlier quoted context omitted.

Survivorship bias. Not disagreeing with you that these are unwatchable, but it’s a little rose-tinted to think that (non-AI) slop didn’t exist a long time ago.

At least non-AI slop had a human behind it.

The AI slop isn't making itself either.

Re: $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

#137
I think that a lot of posters here are missing the point - this is just the tip of the iceberg, and even simple improvements in prompting (infer the meaning of the lyrics, then generate footage related to that) would create a better result.

There is no going back from this, only forwards, for better or worse.

Re: $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

#138
post #72

Earlier quoted context omitted.

Unless I'm misunderstanding the article, or your comment, the models were responsible for generating the music _videos_. The music itself is Uptown Funk... which was a very successful song in 2014 ( https://www.youtube.com/watch?v=OPf0YbXqDm0 ) The videos are indeed awful though.

Yes, I know what the music is. The videos are awful. I meant that watching them is an equivalent experience to listening to music generated by Suno.

They are awful because there is no effort put into it. You're missing the point entirely with generative art. Generative art with care and intent is indiscernible from "real" art at this point. You just don't realize it.

Re: $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

#139
post #13

Earlier quoted context omitted.

I'm classically trained and I honestly can't really tell how these are worse than the human produced ones. They all look kinda the same to me.

Classically trained in music videos??

No, as in classical music. The analog kind.

Re: $100 AI Music Video: Claude Fable 5 vs. GPT-5.6 Sol

#140

This is how you do AI music videos: https://www.youtube.com/watch?v=Njk2YAgNMnE Lean into the not-quite-but-almost uncanny-valley-ness. Make it a feature, not a bug.

They also trained the AI for that video on the band members' own artwork, so the video is focused despite the trippy visuals and avoids copyright issues.
Post reply on HN