[latently]

An interesting technicality from the post and paper is that the measure of causal information (mutual information between the initial and final state) bears some resemblence to the Lyapunov exponent as it is used to measure whether a system is on the edge of chaos. When the exponent is 1 (IIRC) the system does not diverge exponentially when the initial conditions are changed slightly and the system is said to be on the edge of chaos and to have good generalization ability. Anywhere else and the system is either damped or chaotic and you don't expect "interesting" stuff to happen there, such as higher-order "causal" effects. (seriously though, why are people so obsessed with causality when it's clear that there is almost never one "causal" description. let it go!)

[yakult]

Because sometimes there is, and when you know you can control or at least predict the process. Sometimes this makes you mad dosh.