In late 2016 I independently curated a visual map of the areas of research MIRI was working on at the time, together with descriptions of each area and arrows explaining the relationships between areas.

While MIRI's research has evolved since, I have foud myself going back to this map as a reference while doing research, so I though I would share it with the rest of you in case it might be useful for some.

Map of Research Areas in AI Alignment

The map is based on the Agent Foundations agenda by Soares and Fallenstein of 2014 and the Alignment for Advanced ML Systems agenda by Taylor et al in 2016.

Let me know if this was useful for you! It will be useful evidence on whether spending time curating more maps of the same style is a good use of my time.

New Comment
1 comment, sorted by Click to highlight new comments since:

Thanks, great map. It would be also interesting to see which AI safety related fields are not part of the MIRI agenda.