This landscape synthesizes a variety of AI safety research agendas along with other papers in AI, machine learning, and AI safety, robustness, and beneficence research. It lays out what technical research threads can help us build more robust and beneficent AI, and describes how these many topics tie together. The content in this map is also available rendered as an academic paper.
This visualization works better with larger screens as there is a lot of content, it is not ideal for mobile devices as it makes heavy use of mouseovers, and it works best in Chrome or Firefox, with known issues in Internet Explorer/Edge.
Pan: click and drag
Zoom: scroll the mouse wheel, or touchpad equivalent
Node Definition: mouseover the node
Node Discussion and Focus: click on the node
Linkage Explanation: mouseover the orange linkage
To dismiss this purple welcome box, click outside of it.