Superintelligence: Paths, Dangers, Strategies
The human brain has some capabilities that the brains of other animals lack. It is to these distinctive capabilities that our species owes its dominant position. Other animals have stronger muscles or sharper claws, but we have cleverer brains. If machine brains one day come to surpass human brains in general intelligence, then this new superintelligence could become very powerful. As the fate of the gorillas now depends more on us humans than on the gorillas themselves, so the fate of our species then would come to depend on the actions of the machine superintelligence. But we have one advantage: we get to make the first move. Will it be possible to construct a seed AI or otherwise to engineer initial conditions so as to make an intelligence explosion survivable? How could one achieve a controlled detonation? To get closer to an answer to this question, we must make our way through a fascinating landscape of topics and considerations. Read the book and learn about oracles, genies, singletons; about boxing methods, tripwires, and mind crime; about humanity's cosmic endowment and differential technological development; indirect normativity, instrumental convergence, whole brain emulation and technology couplings; Malthusian economics and dystopian evolution; artificial intelligence, and biological cognitive enhancement, and collective intelligence.
1 Past developments and present capabilities
2 Paths to superintelligence
3 Forms of superintelligence
4 The kinetics of an intelligence explosion
5 Decisive strategic advantage
6 Cognitive superpowers
7 The superintelligent will
8 Is the default outcome doom?
12 Acquiring values
13 Choosing the criteria for choosing
14 The strategic picture
15 Crunch time
Other editions - View all
ability achieve action AI’s algorithms approach artificial intelligence behavior biological Bostrom capability Chapter cognitive enhancement collaboration collective intelligence computing power control problem create decision theory decisive strategic advantage digital minds dynamic effect Eliezer Yudkowsky embryos environment evolutionary example existential risks extrapolated volition final goal final value future genetic genie global hardware human human-level humanity’s implement improvements increase individuals instrumental reasons intelligence amplification intelligence explosion learning ligence machine intelligence machine learning machine superintelligence methods Moore’s law moral motivation selection neural neuromorphic neurons optimization power oracle outcome paperclips performance perhaps perverse instantiation physical population possible worlds post-transition potential predict preferences probability recalcitrance reinforcement learning relevant require reward robot scenario seed seed AI simulation singleton social solve specify speed superintelligence superpower takeoff tion transition utility function von Neumann probes whole brain emulation Yudkowsky