General Intelligence

In theory, if you could construct every problem that an 8 year old human can do and you have an AI that solves all of those problems, then you should have an eight year old intelligence. And so that's kind of the philosophy behind what we're doing. The environments that we have today in reinforcement learning and also in machine learning often look very different than the environment that humans spend time in as just one example. We don't have a single goal or single objective function. We have lots of different objective functions. So there's this kind of complex environment that we exist in. One of our hypotheses is if we can construct a similar sort of environment, we say a minimal viable environment that

Transcript

Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app