AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Mercury's Auto GPTs: How They're Moving Fast
There's a lot to be concerned about with auto GPTs. You could be doing exploits and, you know, kind of have it attack vulnerabilities and phishing or human factors,. engineering, lots of different weird things that could start doing. We're working on a bunch of clever ways to work through that. For example, we've built this classifier that understands if something's a claim so we understand if GPT is saying like the sky is green. Well, that's a claim. And I'm trying to protect my receptionist from giving away her password. What are people would try to trick in which way? It might come up with ideas that are just crazy but all of