Comment by occz
7 months ago
You'll be waiting for a long time then, probably. Making codecs is actually a hard problem, the type of thing that AI completely falls over when tasked with.
7 months ago
You'll be waiting for a long time then, probably. Making codecs is actually a hard problem, the type of thing that AI completely falls over when tasked with.
Compression is actually a very good use case for neural networks (i.e. don't have an LLM develop a codec, but rather train a neural network to do the compression itself).
It works amazingly well with text compression, for example: https://bellard.org/nncp/
Considering AI is good at predicting things and that’s largely what compression does, I could see machine learning techniques being useful as a part of a codec though (which is a completely different thing from asking ChatGPT to write you a codec)
Yeah in the future we might use some sort of learned spatial+temporal representation to compress video, same for audio. Its easier to imagine for audio: Instead of storing the audio samples, we store text + some feature vectors that uses some model to "render" the audio samples.
It’s not absurd to think that you could send a model of your voice to a receiving party and then have your audio call just essentially be encoded text that gets thrown through the voice generator on the local machine.
AI video could mean that essential elements are preserved (actors?) but other elements are generated locally. Hell, digital doubles for actors could also mean only their movements are transmitted. Essentially just sending the mo-cap data. The future is gonna be weird
2 replies →