AI/Machine Learning

Here’s what’s dangerous about letting advanced AI control its own feedback

- October 25, 2022 4 MIN READ

How would an artificial intelligence (AI) decide what to do? One common approach in AI research is called “reinforcement learning”. Reinforcement learning gives the software a “reward” defined in some way, and lets the software figure out how to maximise the reward. This approach has produced some excellent results, such as building software agents that… Read more »