next up previous contents
Next: Serious introspection Up: What Consciousness does a Previous: What Consciousness does a

Easy introspection

 

In some respects it is easy to provide computer programs with more powerful introspective abilities than humans have. A computer program can inspect itself, and many programs do this in a rather trivial way by computing check sums in order to verify that they have been read into computer memory without modification.

It is easy to make available for inspection by the program the manuals for the programming language used, the manual for the computer itself and a copy of the compiler. A computer program can use this information to simulate what it would do if provided with given inputs. It can answer a question like: ``Would I print ``YES'' in less than 1,000,000 steps for a certain input? A finitized version of Turing's argument that the halting problem is unsolvable tells us that that a computer cannot in general answer questions about what it would do in n steps in less than n steps. If it could, we (or a computer program) could construct a program that would answer a question about what it would do in n steps and then do the opposite.

We humans have rather weak memories of the events in our lives, especially of intellectual events. The ability to remember its entire intellectual history is possible for a computer program and can be used by the program in modifying its beliefs on the basis of new inferences or observations. This may prove very powerful.

Very likely, computer programs can be made to get more from reading itself than we presently know how to implement.

The dual concept to programs reading themselves is that of programs modifying themselves. Before the invention of index registers (B-lines) at Manchester, programs did indexing through arrays and telling subroutines where to return by program modification. It was sometimes stated that self-modification was one of the essential ideas of using the same memory for programs and data. This idea went out of fashion when major computers, e.g. the IBM 704 in 1955, had index registers.

As AI advances, programs that modify themselves in substantial ways will become common. However, I don't treat self-modification in this article.

Unfortunately, these easy forms of introspection are insufficient for intelligent behavior in many common sense information situations.


next up previous contents
Next: Serious introspection Up: What Consciousness does a Previous: What Consciousness does a

John McCarthy
Mon Jul 15 13:06:22 PDT 2002