On Fri, Dec 28, 2012 at 9:30 PM, Jim Bromer <[email protected]> wrote:
> On Fri, Dec 28, 2012 at 6:09 PM, Logan Streondj <[email protected]>wrote: > >> It's good to get the ideas into something more tangible like programs. >> > > Once you start to create an actual program your original options close in > on your plans. One of the problems in developing a viable AGI program is > that it has to be kept simple. You might have different methods that are > called in for separate cases but that does not always work so well. > You sound like you're coming from Object Oriented perspective, though that really is an outdated form of development, that is incompatible with concurrency, and leads to lots of code duplication. Functional and even procedural paradigms are better suited for code re-use. > > >> >> If you find that after whichever period of time you aren't getting much >> anywhere with your chosen route, perhaps you'll choose to contribute to >> another AGI project, perhaps my own. >> I did a version release today, now have support for primitive variables >> :-). By next version release quite possibly will be able to do factorial or >> some other simple procedures. >> And likely by next year will have English grammar, >> allowing for easier verification by others with smaller learning curve >> > > What does that mean? How does it support primitive variables. And how > would you change your plans if something did not work. For instance, if it > did not have English grammar how would that affect your concepts about AGI? > Er well it currently uses SOV post-position grammar, the most common form of grammar in the world, instead of SVO pre-positions which are used in some of the most popular language such as English, Mandarin and Spanish. Though it is really a very simple transformation to turn it into pre-positions, and then a few inference rules to make it support SVO. So it will certainly have support for English grammar, it's just a matter of time and effort. > The most important thing is to identify problems that can be solved and > problems that you don't have an answer for. After working on logical > satisfiability I have come to the conclusion that I don't have a solution > to logical complexity. So then in order to make my AGI program work it > would have to work by finding a way to overcome the problem of logical > complexity by some other means. > > It would have to acquire a great deal of information by serendipity and > then make 'intuitive' guesses about relations that can only be structured > through correlation and the recognition that if process X could be applied > to situation Y then it suggest a path toward finding a solution. > ? SAT-solving is really a very minor component of making an AGI. I know it was main component of my 4th year AI class, though now the whole program has been canceled. > > > But what if my ideas did not work? Then it would tell me that I had been > making some mistake. If I could find good candidates that kept the program > from working then I should be able to test them pretty quickly. Perhaps > basic correlation is not good enough. Perhaps the program has to rely on > some kind of enhanced correlation where there are numerous reasons to > believe the process X *can* be applied to situation Y and that it *will* > lead to a path toward a solution. > Jim Bromer > > That sound very narrow-AI as your focusing on some problem-solver or something. In reality an AGI is like building a whole brain, it has to do lots of things, including managing it's own software, hardware, keeping track of goals, and a whole slew of things. Due to the incrementality of the roadmap, it is possible to do a little at a time. Having real tangible results every step of the process, building on what was before. Every feature addition is testable an in line with creating a general intelligence operating system or Brain, that can manage a robot-body or even a human community. ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
