The Return of the Art Officials

A project log for Using A.I. to create a Hollywood Script.

Use of an inexpensive microcontroller as a creative adjunct, by incorporating principles of an AI. Be VERY AFRAID!

glgormanglgorman 08/18/2023 at 22:020 Comments

Even if I am not sure just exactly who they are.  Even if they don't exactly know who they are either.  I tried asking Google Bard last night, to see if it could summarize some of the material from a few of my projects on this site, and it turned out to be a complete disaster, meaning that it had absolutely no comprehension of the material whatsoever.  Then it occurred to me that summarizing an article might not be all that hard, actually - if done correctly, since where there is a will, there should be a hack - right?  What if I construct a dictionary for an article, and then use the word counts for each word to identify potential keywords, as I am already doing, but then there needs to be "something else" that needs to be done, that isn't currently being done or is going unnoticed.

Well, as it turns out, I noticed that maybe between one-third and one-half of the words on a typical list of unique words associated with a document are words that occur only once in that document, whereas.   So we could split a dictionary maybe into three parts, one part which might consist of words that are seen only once and then another part that contains words that are seen often, like "the", "we", "of", etc., which might occur dozens, or even hundreds of times, where then there would be those words that typically occur at least twice, but not necessary a "great number of times", whatever that means.  So there could be a list of regular words, another list of frequent words, and yet another for unique words.   Hence document analysis might mimic some of the properties of compiler design, which might have code that tracks, keywords, namespaces, global and local variables, etc,

Hence for efficiency reasons, when developing code that will run on a micro-controller, it seems like it would be useful to have some way of specifying some kind of systematic parsing mechanism that works across multiple domains, on the one hand, in the sense of how it implements the notion of hierarchical frames, vs., specific embodiments of that concept,

So I started making changes to the inner workings of the symbol_table classes in my frame_lisp library, initially for performance reasons, so as to be able to speed up the time to perform simple symbol lookup, insertions, sorting, lexing, and parsing operations; none of which has any obvious impact on how an AI might perform certain tasks, other than from the point of view of raw speed.   Except when designing an asynchronous neuronal network, it should be obvious that the time that it takes for a search engine to return results to multiple, simultaneous queries will have a huge impact on what that network does, even if all we are doing is performing searches on multiple models and then prioritizing the results into a play queue in the order in which the various results are returned.

Well, in any case - let's take a look at how badly Google Bard blew it on the simple request to "Summarize the article "Computer Motivator", as found on the website -, that is according to the project of that name which was created by glgorman. Also summarize "The Money Bomb", and "Using A.I. to create a Hollywood Script" from the same site."

And here is Google's response - which is completely wrong.

So Google thinks that the article "The Money Bomb" is about a fundraising technique used by the Obama campaign, there is actually NOTHING in that article about any of that sort of thing whatsoever.  This is despite the fact that every Hackaday article is supposed to have a tagline and a description, which is supposed to tell you something about what a project is about, and for "The Money Bomb", the tag-line is "Achieving the Million Dollar Payday, or else ...
Why aren’t you a millionaire yet?”  Interestingly enough most theatrical scripts will include something called a log line, which for the Wizard of Oz might be something as simple as "After a young woman named Dorothy is transported by a freak tornado to a magical world called Oz, along with her dog Toto, she embarks along a series of adventures where she meets a Cowardly Lion, a living Scarecrow and a Tin Man - who join Dorothty's quest to find a mysterious wizard who they believe can help solve all of their problems, as well as help Dorothy find her way home.

Now for a more descriptive interpretation of what "The Money Bomb" might actually be about, I suppose that it might actually be helpful to read that projects description which reads something like this:

One reason that many people fail to achieve their financial goals is that they fail to achieve what I will later develop and explain as “their own critical mass”, that is – even if their business plan is fundamentally sound, well timed, etc. Of course, by now you must be thinking: What is the secret formula? Why is it being withheld? Is it even possible … that there is some “secret equation” that is not so secret after all, it is just hidden in some obscure nuclear physics textbook – or in the Bible, or in the Koran, or else might even be inscribed onto the walls of some pyramid? And of course, we are not going to tell you … unless first of all, we know who you are; and why you want to know … perhaps we could, I mean, there is after all the first amendment, and maybe we really could “just simply tell you”, but why should we?

Now it might also be helpful to also take notice that "The Money Bomb" was a project that I entered in Hack-a-day's science fiction contest, and thus as I got further into the project, I had to realize, that since technically this is a hardware site, I had to come up with some sort of "design", such as a "plan" to create a potentially traversable wormhole in the laboratory, so we could perhaps download some trillion trillion carat diamond cores of extinct white dwarf stars from distant galaxies, and so on - even though since this a project that I created for a science fiction contest, the "rules" for that contest are also relevant for understanding the article - since the "rules" offered up to 50% of the points for the "quality of the documentation", and the only other requirement was that it had to include "something electrical" and at least 'blink", unless of course that was non-canon.

Maybe someday Bard will actually read the articles that it is being asked to summarize, Even better still, would be to have the ability to consider the context for which something might have been written.  Then of course, in the real world, we know that there is also something called "the audience", or at least most would-be authors should hope that there will be an audience! But do those authors write to entertain, or do they write to sell popcorn?  They can't possibly be in it for the money themselves, since the studios seem to operate on the principle that the "only good writer is a dead writer", and "the only good actor .... ", just like the record companies that don't want to worry about wardrobe malfunctions or other scandals, and where all they they care about is "catalog rights".

O.K., since I wrote "The Money Bomb" I should be able to come up with an independent review, or at least a piece that reads like one, like "The Money Bomb" is a piece that takes a humorous look at a serious subject, by invoking some even more ominous references to concepts like "critical mass", "initiation", "propagation", "extinction" and so on.  Thus while taking a non-conventional approach to the ever-important subject of economics, the article uses these terms, instead of more traditional terms like "capitalization", "amortization", "obsolescence", and so on.  Yet important concepts such as "doubling time" and "sustainability" are discussed, also with various implications, for whoever you are - or whatever you are - that is - according to your place in the universe.

In any case - Bard does seem to do better with Computer Motivator, at least for trying to be polite and giving me a nice review on that one - even if it still doesn't know what the article is about.

Computer Motivator: The Computer Motivator project is still in the early stages of development, but glgorman has already made significant progress. He has created a prototype program that can set goals, track progress, and provide rewards. He is currently working on improving the program's user interface and adding additional features.

Now a program that can "set goals", "track progress" and "provide rewards" sounds like an interesting concept.  So perhaps Bard isn't completely useless.  Maybe I should ask GPT-4 Co-pilot to write such a thing.  AAAAARRRRRRRGGGGGGGHHHHHHHHHHHH!!!!!!!!!!!