Read the original document by opening this link in a new tab.
Table of Contents
1. Introduction
2. The evolution of intelligence
2.1. A story
3. Abstraction as a dangerous weapon
3.1. A continuing story
4. Incremental intelligence
Summary
This paper describes research done at the Artificial Intelligence Laboratory of the Massachusetts Institute of Technology. It outlines an approach to incrementally building complete intelligent creatures by decomposing the system into independent and parallel activity producers that interface directly with the world through perception and action. The paper argues for a different approach to creating artificial intelligence, emphasizing the incremental development of complete intelligent systems. It discusses the evolution of intelligence, the dangers of abstraction, and the importance of building autonomous mobile agents known as Creatures.