audio models
1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement May 16, 2024 by Mikey Shulman · across every show →
Everything said about audio models, oldest first
May 16, 2024 negative
AI evaluation benchmarks fail for audio, necessitating human aesthetic judgment
“I think in, in all branches of AI, we become slaves to our metrics, and you say, I did this accuracy on this benchmark, and this accuracy on this benchmark, and in the real world, sometimes it doesn't necessarily matter, and these benchmarks are extra terrible…”