Hi Mike (Tintner), You've often made bold claims about what "all AGIers" do or don't do. This is despite the fact that you haven't met me in person and I haven't revealed many of my own long term plans on this list (and I'm sure I'm not the only one): you're making bold claims about *all* of us, without actually knowing what we're *all* doing. When you first joined the group, I tried to point out that many AGI and AI people are trying to do the very thing that you claim we aren't doing (and many others have similar done likewise). Please don't talk about "all AGIers" until you have met every single one.
Anyway, for the point of discussion I thought I'd give your "ideas" a moment and actually try your suggestions. You sometimes you talk about the grand goals of AGI and complex human behaviours, as though you're the only one who sees this. This isn't necessary, most of us share such goals - I can see this in the work of any researcher in the area. These grand goals, however, are quite difficult and it will take time to get there. What we need is a plan on how to get there, and some kind of easier-to-reach stepping stones along the way. These stepping stones are what characterizes most current research... steps, that I believe clearly point towards the long term objective. You seem to think that these steps have nothing to do with the real problem. It appears that you view artistic acts as the crucial problem of intelligence. So let us look at free association, as you have recently done. I found your free association lists silly and nonsensical. For example, in one list you "free associate" nose with Afghanistan and oxygen with eyes. They seem silly because the association depends on some hidden steps (that you only explained later). I think the lists would be a lot better if you made the steps explicit. (e.g., replace oxygen-eyes with something like oxygen-invisible-eyes or oxygen-everywhere-visible-eyes, or whatever it was that you were thinking). Okay. So, let's keep it simple. Let's do free association where each step has to make some kind of sense, and where we only deal with single words. Surely this is a sensible stepping stone to AGI? Well, as Matt said, this actually turns out to be quite simple. I've put together a "free association" machine. Give it a fairly common word, and it will free-associate from there to create a list of 15 words. http://www.comirit.com/freeassoc/ Every single list will be unique. Every single list combines randomness with structure. Every list crosses domains, and if you compare the first word to the last word (in light of the words in-between) you see that a very original kind of analogy has apparently taken place. This is, as far as I can tell, what you've been talking about. But this isn't AGI. This isn't even interesting AI. I hope that you're also ready to give your own argument for why it isn't AGI. The thing is, however, that something like this free association machine seems to be the very thing that you're pointing to. A similar approach can be used to generate somewhat-structured and somewhat-unstructured drawings like on that imagination3 site that you thought could be the basis of a mathematical formalization. (I'm not going to tell you how it works - it uses a very dirty trick - the point is, though, that it gives the appearance of intelligence and seems to do what you want it to do) It didn't take me long to put this together - in fact, the hardest bit was just working out how to upload it to my server. I think creativity and artistic expression are poor choices for exploring AGI, they are too subjective to be measured and it seems easier to fool people into thinking a pattern looks creative and artistic than it is to create a pattern that solves some measurable problem. However, when I begin to speculate what I would need to do to improve the free association machine to make it into an interesting piece of AI, I find that logics, probabilistic logics, evolutionary learning, search, complex systems, structure mapping, neural networks would all jump out as interesting avenues to explore. In other words, creativity and artistic expression bring us to EXACTLY the same core problems; but in a domain that seems to me to be less amenable to productive, measurable or even profit-generating research. It certainly isn't a given that creativity and art is the only approach to AGI. In fact, after we get over that very first hurdle of making something appear to be artistic, we're at exactly the same problems that are encountered in every other problem domain: problems of learning and building problem-solving representations automatically - the very problems that motivate AGI researchers every day. So, I tried your suggestion. After getting past that first step of writing the version-zero free associator, I found myself in exactly the same place as I was before and facing exactly the same problems, but in a problem domain that is less useful that what I was already working in. I also think this program highlights the fact that you really should learn computer programming before criticising what we do. You jump from describing problems that seem laughably trivial (in a certain light) and then try to relate this to the big challenges (that we're all fully aware of and trying to solve). With no middle-ground-problems, your comments sound like you don't really understand the situation yourself. If you wanted to offer something useful, rather than simply being argumentative, then an understanding of what is and isn't achievable in computer languages would help you understand the real challenges in AGI, and let you formulate meaningful stepping stones. -Ben ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=126863270-d7b0b0 Powered by Listbox: http://www.listbox.com
