"It seems to me that the notion of machine that was current in the course of the Industrial Revolution – and which we might have inherited – is a notion, essentially, of a machine without goal, it had no goal ‘of’, it had a goal ‘for’. And this gradually developed into the notion of machines with goals ‘of’, like thermostats, which I might begin to object to because they might compete with me. Now we’ve got the notion of a machine with an underspecified goal, the system that evolves. This is a new notion, nothing like the notion of machines that was current in the Industrial Revolution, absolutely nothing like it. It is, if you like, a much more biological notion, maybe I’m wrong to call such a thing a machine; I gave that label to it because I like to realise things as artifacts, but you might not call the system a machine, you might call it something else."

“... checks the relevance of the information entering his list by forming single predicate hypotheses .... A structure is built up in orderly stages.”

“Since human beings are highly adaptable it may be possible for an individual with any sort of competence to learn, in the end, according to any teaching strategy. But the experiments show, very clearly indeed, that the rate, quality and durability of learning is crucially dependent upon whether or not the teaching strategy is of a sort that suits the individual”

“A computer that issues a rate demand for nil dollars and nil cents is not a maverick machine. It is a respectable and badly programmed computer... Mavericks are machines that embody theoretical principles or technical inventions which deviate from the mainstream of computer development, but are nevertheless of value.”

“If cognitive processes can be realized in a general machine then it is possible to execute mental operations in artifacts that are not necessarily subject to the embarrassing spatio-temporal limitations and structural frailties of a biological processor.”

“A learning strategy is comparable in kind with a performance strategy. Each sort of strategy entails decomposing goals into subgoals and applying mental subroutines to achieve the subgoals concerned. The necessary difference between learning strategies and performance is in the domain upon which they operate. Whereas the performance strategy solves problems posed by states of the environment, the learning strategy solves the problems posed by deficiencies in the current repertoire of relevant performance strategies; the solutions produced by a learning strategy are performance strategies.”

“Cybernetics offers a scientific approach to the cussedness of organisms, suggests how their behaviours can be catalysed and the mystique and rule of thumb banished.”