|
| ▲ | true_religion 17 hours ago | parent | next [-] |
| Sounds like it would be susceptible to how they’d reverse engineer LLMs using distillation. |
| |
| ▲ | tyromaniac 10 hours ago | parent [-] | | Connect the dots for me, I'm not seeing it. Unless you are talking about building a function approximator for a bunch of measured transfer characteristics, in which case you could as easily do that well before AI. |
|
|
| ▲ | pjc50 15 hours ago | parent | prev | next [-] |
| The several seconds of latency would be fun. |
| |
|
| ▲ | wazoox 4 hours ago | parent | prev | next [-] |
| That's basically how convolution reverb has worked for 25 years. |
|
| ▲ | casey2 6 hours ago | parent | prev [-] |
| since human hearing is lossy you can get whatever sound you like. In the context of a moat there is none for a sfx |
