←back to thread

Ovi: Twin backbone cross-modal fusion for audio-video generation

(github.com)
280 points montyanderson | 1 comments | 22 Oct 25 19:42 UTC | HN request time: 0.198s | source
Show context
amelius ◴[22 Oct 25 20:57 UTC] No.45675056[source]▶
How long until we see blockbuster movies produced by a guy in his basement for <$1000?
replies(17): >>45675093 #>>45675094 #>>45675098 #>>45675190 #>>45675223 #>>45675247 #>>45675311 #>>45675313 #>>45675412 #>>45675429 #>>45675453 #>>45675483 #>>45675530 #>>45675818 #>>45675994 #>>45676309 #>>45676702 #
roarcher ◴[22 Oct 25 21:11 UTC] No.45675190[source]▶
Never. I've seen people instantly go from liking a static image to disliking it upon learning it was AI generated. The same applies to other kinds of media. No matter how "good" it is, knowing that it was created by an unfeeling algorithm ruins it for most people.
replies(6): >>45675290 #>>45675291 #>>45675349 #>>45675541 #>>45676103 #>>45677207 #
jonwinstanley ◴[22 Oct 25 21:20 UTC] No.45675291[source]▶
This is defo true until the moment it gets so good people can't tell.
replies(2): >>45675338 #>>45677014 #
1. numpad0 ◴[23 Oct 25 00:57 UTC] No.45677014[source]▶
you see, I think there's a huge oversight in that sentence. People don't enjoy analysis of an art, people feel positive from looking at one and like doing it.

they're not doing enough to optimize AI data generators for dopamine release with animalistic obsession. Instead they focus on scientific indistinguishablilitiness, and people aren't liking that. IMO that's has been an ongoing and growing costly mistake.