p.3 This property of inevitably finding some stable state was the key attribute of the homeostat. The homeostat
was an example of what Ashby called an ultrastable system... so what? What's so great about ultrastability?
...what strikes me about them [JLJ - 4 individual units were often connected together in a configuration
useful for a practical demonstration] is their liveliness. I can't actually think of any prior example
of a real machine that would randomly - open-endedly as I would say - reconfigure itself in response to its inputs.
p.4 It seems reasonable, then to speak of the homeostat as having a kind of agency - it did things in the world that
sprang, as it were, from inside itself, rather than having to be fully specified from outside in advance.
p.4-5 The homeostat was an electromechanical proto-brain, and both Ashby and Beer took it very seriously as such... the
homeostat was a model of the brain as an adaptive controller of behaviour, and Ashby took this idea very far. He noted, for
instance, that, as so far described, the homeostat might be a brain, but that it would be hopelessly inefficient in complex
situations.
