Comment on OpenAI Quietly Deletes Ban on Using ChatGPT for “Military and Warfare”
Jknaraa@lemmy.ml 10 months agoI can’t wait until people find out that you don’t even need to train it on secrets, for it to “leak” secrets.
Comment on OpenAI Quietly Deletes Ban on Using ChatGPT for “Military and Warfare”
Jknaraa@lemmy.ml 10 months agoI can’t wait until people find out that you don’t even need to train it on secrets, for it to “leak” secrets.
Kase@lemmy.world 10 months ago
How so?
Jknaraa@lemmy.ml 10 months ago
Language learning models are all about identifying patterns in how humans use words and copying them. Thing is that’s also how people tend to do things a lot of the time. If you give the LLM enough tertiary data it may be capable of ‘accidentally’ (read: randomly) outputting things you don’t want people to see.
uranibaba@lemmy.world 10 months ago
But how would you know when you have this data?
Jknaraa@lemmy.ml 10 months ago
It may prompt people to recognizing things they had glossed over before.