oter

Machines must learn from human feedback from "summary" of Human Compatible by Stuart Russell

The key idea here is that machines must be designed to learn from human feedback. This is crucial because human values are complex and can't easily be programmed into machines in advance. Instead of trying to specify all possible situations and outcomes in advance, we need machines that can learn from feedback as they interact with the world. The reason is that our values and preferences are not fixed or universal; they can change over time, and they vary from person to person. So if we want machines to act in ways that are aligned with human values, they need to be able to learn from us. One approach to building machines that can learn from humans is reinforcement learning, where the machine receives feedback in the form of rewards or penalties based on its actions. This feedback allows the machine to learn what actions lead to positive outcomes and which ones lead to negative outcomes. By adjusting i...
    Read More
    Continue reading the Microbook on the Oter App. You can also listen to the highlights by choosing micro or macro audio option on the app. Download now to keep learning!
    oter

    Human Compatible

    Stuart Russell

    Open in app
    Now you can listen to your microbooks on-the-go. Download the Oter App on your mobile device and continue making progress towards your goals, no matter where you are.