Simple core is a term that has been used to describe various things in AI safety. I think the "simple" part is intended to capture that the thing is human-understandable or even something like 'able to be described by a few mathematical equations'. And the "core" part is intended to say that there might be other more complicated things in addition.
- Simple core to corrigibility
- Simple core of consequentialist reasoning
- Simple core to AI safety techniques
- Simple core for impact measures