Not sure how to clarify. AI capabilities research consists of looking for computer programs that do lots of different stuff. So you’re selecting for computer programs that do lots of different stuff. The claim is that that selection heavily upvotes algorithms that tend towards coherence-in-general.
I did not understand anything from what you said… How does coherence generate an equivalent of an internal “push” to do something?
Not sure how to clarify. AI capabilities research consists of looking for computer programs that do lots of different stuff. So you’re selecting for computer programs that do lots of different stuff. The claim is that that selection heavily upvotes algorithms that tend towards coherence-in-general.