Epstein Secrets

more complex than they first appear. They are infinite, yet there are different infinities, and they have meaning. The smallpox example above and the Turing numbers we will discover shortly suggest numbers do have meaning independent of culture and language. The next two chapters will show us what happens

away their secrets. The Enigma machine was an elegant compromise between a truly unbreakable code and a simple cipher. Unfortunately for the Germans, Turing was on the side of the Allies. In the 1930s almost all mathematics, accounting, and code-breaking were performed by humans using pencil and paper. I

’s Chinese Room, this is the same process the man in the room followed: get a symbol, look it up in a book, and reply with the corresponding symbol. Universal Turing Machine We have missed one important step from our explanation of the modern computer: the ability to run programs. Nowadays, we take for granted you can do

at they tend to favor or ignore. Surely (ding!)?, any man who could beat a woman at being perceived to be a woman would be an intelligent agent. What Turing did not foresee is the power of deep-learning AI to acquire this wealth of information in an exploitable form without having to understand it. Turing

the CIRL framework, one can formulate and solve the off-switch problem—that is, the problem of how to prevent a robot from disabling its off-switch. (Turing may rest easier.) A robot that’s uncertain about human preferences actually benefits from being switched off, because it understands that the human w

ifferent machine was required for each separate computational problem; later work by others would show that in one particular machine, now known as a Universal Turing Machine, an arbitrary set of computing instructions could be encoded on that same tape. In the 1940s, von Neumann developed an abstract self-reproducing mac

at they tend to favor or ignore. Surely (ding!)?, any man who could beat a woman at being perceived to be a woman would be an intelligent agent. What Turing did not foresee is the power of deep-learning AI to acquire this wealth of information in an exploitable form without having to understand it. Turing

the CIRL framework, one can formulate and solve the off-switch problem—that is, the problem of how to prevent a robot from disabling its off-switch. (Turing may rest easier.) A robot that’s uncertain about human preferences actually benefits from being switched off, because it understands that the human w

ifferent machine was required for each separate computational problem; later work by others would show that in one particular machine, now known as a Universal Turing Machine, an arbitrary set of computing instructions could be encoded on that same tape. In the 1940s, von Neumann developed an abstract self-reproducing mac