No seriously. A good mathematical model of AGI, say lowest common denominator, created in category theory where all real AGI's are isomorphic to it. Make it abstract and minimalistic as possible. In the generator you have to include numerous mappings between math and source code so the thing spews out unoptimized c++ code for any possible construct it can think of and knows how to merge and combine well. It has to be able to manage chunks of code and compile, test, generate tests, combine sub-modules, modules, etc.. I think it's doable. Naturally the problems of resources, optimization, compiler bugs, the hairy stuff will still be there. But the idea is to have machines working for man not man working for machines right?
John > From: Jiri Jelinek [mailto:[EMAIL PROTECTED] > Go ahead :).. If you have *enough* time, almost no thinking is needed: > Many think smart AGI can fit into as little as 100KB. Have ~1K of data > sufficient for solving a couple of very tricky problems, generate all > possible combinations of bits for 100K file, run each instance in some > kind of protected mode with access to the 1K data, ask it to solve the > tricky problems and auto-check the solution. Happy waiting! ;-)) > ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=231415&user_secret=e9e40a7e
