We don't know what's going on inside these models right now. They're black boxes. And so an example that most people aren't aware of is that when they release GPD4, they actually like tried to see if it would escape and take over the world. It was able to hire a worker off task rabbit because they got stuck at a capture but still couldn't pass the capture. That could mean making money out of tricking you into doing something wrong. Just imagine a human who read every book ever published and the entire internet. The head of the joke here is I'm basically trying to persuade each other to do things we wouldn't want to do in our own lives.
Emerson Spartz has been building internet and media companies since starting MuggleNet, the world's largest Harry Potter fan site, when he was just 12 years old. He founded digital media company Dose which created some of the world's largest viral content sites. For the past few years, Emerson has been focused on AI, with a particular interest in AI safety, AI alignment and extinction risk. Despite being such a techno-optimist by nature that he's been yelled at for being a techno-optimist in books, he has come to have real concerns about the speed and way that AI is developing. In this sprawling conversation, Emerson provides a set of mental models he uses to try and understand AI broadly. Recommended resources: https://aisafety.info/ Robert Miles YouTube - https://www.youtube.com/c/robertmilesai The A.I. Dilemma - https://www.youtube.com/watch?v=xoVJKj8lcNQ The AI Breakdown helps you understand the most important news and discussions in AI.
Subscribe to The AI Breakdown newsletter: https://theaibreakdown.beehiiv.com/subscribe
Subscribe to The AI Breakdown on YouTube: https://www.youtube.com/@TheAIBreakdown
Join the community: bit.ly/aibreakdown
Learn more: http://breakdown.network/