Algorithmic model building in artificial intelligence provides a contemporary method for explaining certain kinds of human behavior. The paranoid mode of thought and action represents a kind of pathological behavior that has been well recognized for over twenty centuries. This article describes a computer simulation model embodying a theory that attempts to explain the paranoid mode of behavior in terms of strategies for minimizing and forestalling shame-induced distress. The model consists of two parts, a parsing module and an interpretation-action module. To bring the model into contact with the conditions of a psychiatric diagnostic interview, the parsing module attempts to understand the interview input of clinicians communicating in unrestricted natural language. The meaning of the input is passed to an interpretation-action module made up of data structures and production rules that size up the current state of the interview and decide which (linguistic) actions to perform in order to fulfill the model's intentions. This module consists of an object system which deals with interview situations and a metasystem which evaluates how well the object system is performing to attain its ends. The fidelity of the simulation has been tested using Turing-like indistinguishability tests in which clinical judges attempt to distinguish the paranoid model-patient from an actual paranoid patient. Since clinicians are unable to make the relevant distinctions, the simulation is considered successful at the input-output level of functional equivalence. Issues of underlying structural equivalence and the nature of generative pattern explanations are discussed in the light of the model's potential value in guiding clinicial decisions and intervention strategies in paranoid disorders.