Prompt Armor
1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Feb 8, 2024 by Garry Tan · said 4 times in 1 episodes since 2024 · across every show →
Mentions by year
brought up most by Garry Tan (4)
tap a year for its mentions
2024 4 mentions in 1 episode
Everything said about Prompt Armor, oldest first
Feb 8, 2024 negative
Tan: Fine-tuning models on private data risks leaking it through prompts
“What they actually have figured out is that for a lot of large language models, if you do any sort of fine tuning or training with private data, you can actually just speak to the model and get it to spit out your private data again, and they have a solution t…”