I'll be giving a 35-minute talk to some folks from Rutgers philosophy and Giving What We Can, followed by Q and A, informal discussion, and hopefully conversation that continues over pizza or something. Come meet me, Carl Shulman (another SingInst research fellow; also, by husband:)), me, and other LW-ers, discuss some ideas, and have fun! * * * The abstract that was sent out to Rutgers folk: In 1965, I.J. Good proposed that machines would one day be smart enough to make themselves smarter. Having made themselves smarter, they would spot still further opportunities for improvement, quickly leaving human intelligence far behind. He called this the "intelligence explosion". I review the argument for an intelligence explosion, and how one might seek to influence its outcome, and reduce the odds of catastrophe, should such an event occur. I also try, very briefly, to situate such interventions in relation to other paths for doing good, such as third world poverty interventions and interventions to reduce nuclear risk.