AI today is comparable to physics in the 1700s. Back then, it was a bunch of people tinkering with prisms and apples. Today, it's a bunch of people tinkering with hyperparameters. I suspect that we know as little about AGI today as someone in the 1700s knew about QFT. Not only did they not know about QFT, but they didn't even know that they didn't know it.
Wouldn't it be fun if the next Newton turns out to be the guy who wrote Doom and other FPS, games that were blamed for any kind of surge of violence until the GTA games show up?
Too many people make this mistake of conflating machine learning with AI. I hope someone as external to the field as Carmack will see the value of rule based inference as well. The Good Old Fashioned AI as it used to be called
