I expect Magnus Carlsen to be closer in ELO to a bounded superintelligence than to a median human.
Seems like this sort of claim could be something tractable that would qualify as material progress on understanding bounds to superintelligence? I’m thinking about results such as this.
However I think that post’s title oversells the result—from the paper:
This paper has demonstrated that even superhuman agents can be vulnerable to adversarial policies. However, our results do not establish how common such vulnerabilities are: it is possible Go-playing AI systems are unusually vulnerable.
There may be superhuman go playing models that are more robust.
I’m also just noting my thoughts here, as I’m also very interested in foom dynamics and wondering how the topic can be approached.
Seems like this sort of claim could be something tractable that would qualify as material progress on understanding bounds to superintelligence? I’m thinking about results such as this.
However I think that post’s title oversells the result—from the paper:
There may be superhuman go playing models that are more robust.
I’m also just noting my thoughts here, as I’m also very interested in foom dynamics and wondering how the topic can be approached.