It’s actually rather hard to fill the roster with people who have much new and interesting to say on core issues. At the present margin my sense is that this is limited on the supply side.
That’s an interesting claim. Is there really a tiny set that has new and interesting things to say or is that that set intersected with the set of willing speakers is small? The first is surprising and disturbing. The second seems much less so.
There are very few folk who are working on the topic as such, or have written something substantial about it, and a large fraction of those have already spoken. Maybe you could name 10 candidates to give a sense of who you’re thinking of? Speakers are already being sought for next year’s Summit and good suggestions are welcome.
Some folk are hard to get in any given year because of their packed schedules or other barriers, even though we would want them as speakers (e.g. Bill Joy, various academics) although this becomes easier with time as people like Peter Norvig, Rodney Brooks, Jaan Taallinn, Justin Rattner, etc speak. Others have some interesting things to say, but are just too low-profile relative to the expected value of their talks (such that if SI accepted all such people the Summit’s reputation and attendance would be unsustainable). Or, they may just be “in the closet” so that we have no way to locate them as folk with new non-public insights on core issues.
I was thinking for example Scott Aaronson if you could get him to give a talk. I’d be interested in for example what he would have to say about theoretical computer science being relevant for AI undergoing fast recursive self-improvement. He’s also wrote more generally about philosophical issues connecting to computational complexity some of which might be more directly relevant to Friendly AI.
Folk around here talk to Scott reasonably often. In my experience, he hasn’t been that interested in the core issues you were talking about. A generic tour of computational complexity theory would seem to go in the same category as other relatively peripheral talks e.g. on quantum computing or neuroimaging technology. You’re right that the philosophy and computer science stuff he has been doing recently might naturally lend itself to a more “core” talk.
It’s actually rather hard to fill the roster with people who have much new and interesting to say on core issues. At the present margin my sense is that this is limited on the supply side.
That’s an interesting claim. Is there really a tiny set that has new and interesting things to say or is that that set intersected with the set of willing speakers is small? The first is surprising and disturbing. The second seems much less so.
There are very few folk who are working on the topic as such, or have written something substantial about it, and a large fraction of those have already spoken. Maybe you could name 10 candidates to give a sense of who you’re thinking of? Speakers are already being sought for next year’s Summit and good suggestions are welcome.
Some folk are hard to get in any given year because of their packed schedules or other barriers, even though we would want them as speakers (e.g. Bill Joy, various academics) although this becomes easier with time as people like Peter Norvig, Rodney Brooks, Jaan Taallinn, Justin Rattner, etc speak. Others have some interesting things to say, but are just too low-profile relative to the expected value of their talks (such that if SI accepted all such people the Summit’s reputation and attendance would be unsustainable). Or, they may just be “in the closet” so that we have no way to locate them as folk with new non-public insights on core issues.
I was thinking for example Scott Aaronson if you could get him to give a talk. I’d be interested in for example what he would have to say about theoretical computer science being relevant for AI undergoing fast recursive self-improvement. He’s also wrote more generally about philosophical issues connecting to computational complexity some of which might be more directly relevant to Friendly AI.
Folk around here talk to Scott reasonably often. In my experience, he hasn’t been that interested in the core issues you were talking about. A generic tour of computational complexity theory would seem to go in the same category as other relatively peripheral talks e.g. on quantum computing or neuroimaging technology. You’re right that the philosophy and computer science stuff he has been doing recently might naturally lend itself to a more “core” talk.
Any others?
Not that immediately comes to mind, no.