differentially private language model training
1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Jul 2, 2025 by Jack Morris · across every show →
Everything said about differentially private language model training, oldest first
Jul 2, 2025 negative
Morris: Open model creators do not use differential privacy or anonymization
“I would be extremely surprised if they do any type of like private training. Like there are these mechanisms for doing like differentially private language model training, or even just anonymization in the pre-training pipeline. I bet they don't do any of that…”