Cybersecurity and AI
The Lawfare Podcast
00:00
The Threat to the Algorithms
Large language models are capable of doing tasks, right? And we've already done some experimentation. Some other folks have started to write papers about this with giving the model a prompt that is a set of instructions for how to moderate or label a piece of content. We think it is very likely that it will be able to do that sort of image level moderation as well.
Transcript
Play full episode
