If we are to understand the interactions of a large number of agents, we must first be able to describe the capabilities of individual agents.

The recycling of resource by the aggregate behavior of a diverse array of agents is much more than the sum of the individual actions.

The measure of performance of any given agent is the amount of money it accumulates through its actions.

When a new building block is discovered, the result is usually a range of innovations.

Evolution continually innovates, but at each level it conserves the elements that are recombined to yield the innovations.

Holland's and Kauffman's work, together with Dawkins' simulations of evolution and Varela's models of autopoietic systems, provide essential inspiration for the new discipline of artificial life, This approach, initiated by Chris Langton (1989, 1992), tries to develop technological systems (computer programs and autonomous robots) that exhibit lifelike properties, such as reproduction, sexuality, swarming, and co-evolution.

Unwrapping occurs when the "solution" is explicitly built into the program from the start.