cads: "The Skynet hypothesis is a boogeyman intended to scare the young and the paranoid. The real threat from AI is that it will become so good at the pointless tasks that we have given it that those pointless tasks will become a black hole of resources." I am reading an article about a concept the author calls malignant computing - computing that increases itself and hurts the market in an effort to perpetuate itself. http://radar.oreilly.

cads: it's the classic romanian "you know theory but you don't know practice" attack "o ai cu teoria. Dar practica te omoare." classic because every romanian has heard it from every other romanian they know, in one situation or another.

cads: I came up with the idea of encrypted computing when I was thinking how to design an autonomous AI agent that cannot ever have its state vector interrogated or partially simulated.

cads: in any case, the full problem is an interesting problem in the logging literature and in the AI literature - given some collection of possibly contradictory logs, process them into a single, more trustworthy digest log