Designing Rational, Self-Improving AI

Sounds strangely like agent-based models:

I interviewed Steve Omohundro prior to the Singularity Summit 2007 about his notions of developing artificial general intelligences (AGIs), but he went into far more detail about his views. He applies what he called “microeconomic rationality,” from the work of John Von Neumann and others, to building intelligent, well meaning machines.

Read much more after the link.

See my previous posts on agent-based models (something I hope to make a significant part of my future research):

• Agent-Based Computer Models Revolutionize Social Science Research
• Complexity Economics
• Consider the Ant!