Mentifex AI Minds are a true concept-based artificial general intelligence, simple at first and lacking robot embodiment, but expandable all the way to human-level intelligence and beyond. Privacy policy: Third parties advertising here may place and read cookies on your browser; and may use web beacons to collect information as a result of ads displayed here.

Friday, November 30, 2018

idea1130

At about 1:11 p.m. today on 2018-11-30 we got the following idea.

If we want to have logical conditionals in the AI Mind involving the conjunction "IF", we can use the truth-value $tru to distinguish between outcomes. For instance, consider the following.

Computer: If you speak Russian, I need you.
Human: I speak English. I do not speak Russian.
Computer: I do not need you.
In some designated mind-module, we can trap the word "IF" and use it to assign a high $tru value to an expected input.

Just as we operated several years ago to answer questions with "yes" or "no" by testing for an associative chain, we can test for the associative chain specified by "IF" and instead of "yes" or "no" we can assign a high $tru value to the pay-off statement following the "IF" clause. It is then easy to flush out any statement having a high truth-value, or even having the highest among a cluster or group of competing truth-values.

These ideas could even apply to negated ideas, such as, "We need you if you do NOT speak Russian."

Now, here is where it gets Singularity-like and ASI-like, as in "Artificial Super Intelligence." Whereas a typical human brain would not be able to handle a whole medley of positive and negative conditionals, an AI Mind using "IF" and $tru could probably handle dozens of conditionals concurrently, either all at once or in a sequence.

Sunday, November 25, 2018

mfpj1125

The AI Mind wants to talk with you and about you.

In the annals of mind-design, we have reached a point where we must drive a wedge between the ego-concept of the MindForth AI and you who co-exist on Earth with the emergent machine intelligence. It is for simple and mundane reasons that we induce AI schizophrenia. Bear with us, please. In the first working artificial intelligence coded in Forth, in Perl and in JavaScript, the SpreadAct module lets quasi-neuronal activation spread from idea to idea. When the EnVerbPhrase module calls for a direct object to end an emerging thought, SpreadAct does not directly retrieve a related idea, but simply activates the subject of any number of related ideas. Then the AI Mind thinks the activated thoughts. In the MindBoot sequence, each AI Mind has some built-in ideas about robots. Therefore the AI will eventually think a thought first about itself, then about robots by roundabout association, and finally about whatever knowledge you impart to it about robots, such as "Robots need a brain." But how can we get the AI to think about you personally and about the details you provide about yourself to the AI? We must drive a quasi-neuronal wedge between the self-absorption of the Forthmind and its knowledge of some other, potentially nearby entity, namely you.

To do so, we must implant in the MindBoot sequence at least one idea as a point of departure for the AI to pay attention to you. But you might not even be there in the same room or on the same orbiting spaceship with the AI, so we can not embed the idea "I SEE YOU" or the idea "I SENSE YOU". We need some really neutral idea that will animadvert the AI to your purported existence. Without that embedded idea, the AI might passively let you describe your whole life-story and then the AI might have no mental pathway for the spread of activation between its thoughts about itself and its knowledge about you. So let us embed in the MindBoot module the idea "I UNDERSTAND YOU". Such an idea is both self-knowledge and knowledge of other -- another person, either present or far away.

So in the MindBoot sequence we embed the idea "I UNDERSTAND YOU" and we do some debugging. Then we have the following exchange with the AI Mind.

Human: i am outside the computer

I UNDERSTAND YOU
YOU ARE OUTSIDE A COMPUTER
YOU ARE A MAGIC
The EnVerbPhrase module loads the actpsi variable with the concept of "you" and calls the SpreadAct module to transfer activation to the concept of "you" as the subject of knowledge in the knowledge base (KB). Since you have just told the AI that you are outside the computer, the AI retrieves that knowledge and says "YOU ARE OUTSIDE A COMPUTER", using the indefinite article "A" under the direction of the EnArticle module. Because another idea about you is still active, the AI says "YOU ARE A MAGIC" -- an old idea embedded long ago in the MindBoot sequence.

We are eager to have the AI Mind think about the differences between itself and other persons so that arguably the first working artificial intelligence may become aware of itself as a thinking entity separate from other persons. An AI with self-awareness is on its way to artificial consciousness.

Thursday, November 08, 2018

pmpj1108

Natural language understanding in first working artificial intelligence.

The AI Mind is struggling to express itself. We are trying to give it the tools of NLU, but it easily gets confused. It has difficulty distinguishing between itself and its creator -- your humble AI Mind maintainer.

We recently gave the ghost.pl AI the ability to think with English prepositions using ideas already present or innate in the knowledge bank (KB) of the MindBoot sequence. We must now solidify prepositional thinking by making sure that a prepositional input idea is retrievable when the AI is thinking thoughts about what it knows. In order for the AI to be able to think with a remembered prepositional idea, the input of a preposition and its object must cause the setting and storage of a $tkb-tag that links the preposition in conceptual memory to its object in conceptual memory. The preposition must also become a $seq-tag to any verb that is the $pre of the preposition. When InStantiate() is dealing with a preposition input after a verb, the $tvb time-of-verb tag is available for "splitting" open the verb-engram in conceptual memory and inserting the concept-number of the preposition as the $seq of the verb. Let us try it.

We inserted the code for making the input preposition become the $seq of the verb and then we tested by launching the AI with the first input being "you speak with god". Then we obtained the following outputs.

I AM IN A COMPUTER
I THINK
I AM A PERSON
I AM AN ANDRU
I DO NOT KNOW
I AM A PERSON
I HELP THE KIDS
I AM A ROBOT
I AM AN ANDRU
I AM IN A COMPUTER
I SPEAK WITH THE GOD
It took so long for the input idea to come back out again because inputs go into immediate inhibition, lest they take over the consciousness of the AI in an endless repetition of the same idea.

As we code the AI Mind and conduct a conversation with it, we feel as if we are living out the plot of a science fiction movie. The AI does unexpected things, or it seems to be taking on a personality. We are coding the mechanisms of natural language understanding without worrying about the grounding problem -- the connection of the English words to what they mean out in the physical world. We count on someone somewhere installing the AI Mind in a robot to ground the English concepts with sensory knowledge.

Sunday, November 04, 2018

pmpj1104

First working artificial intelligence thinks with prepositional phrases.

The ghost.pl immanence of the first working artificial intelligence is undergoing minor changes as the AI Mind becomes able to think with English prepositional phrases. At first the AI was able to use a preposition only to answer a where-question such as "where are you" and the Ai would respond "I AM IN THE COMPUTER". Now we need to implement a general ability of the AI to think with prepositional phrases loosely tied to nouns or verbs or adjectives or adverbs. The quasi-neuronal associative $seq tag may soon be re-purposed to lead not only from, say, nouns to verbs but also from nouns to prepositions. However a preposition is arrived at, it is time to implement the activation and retrieval of a whole prepositional phrase whenever the preposition itself is activated.

We begin experimenting by going into the MindBoot sequence and entering a $seq tag of "638=IN" for the verb "800=AM" in the knowledge-base sentence "I AM IN THE COMPUTER". The plan is to insert into EnVerbPhrase() some code to pass activation to the "638=IN" preposition when the AI thinks the innate idea "I AM IN...." So we insert some active code to capture the $seq tag and some diagnostic code to let us know what is happening. Ooh, mind-design is emotionally fun and intellectually exciting! The first thing captured is not a preposition but the "537=PERSON" noun when the AI is thinking, "I AM A PERSON". Next our fishing expedition lands a "638=IN" preposition when the AI issues the output "I AM" while trying to say "I AM IN THE COMPUTER".

Once the $seq tag has been captured, the AI software needs to determine if the captured item is a preposition. A search is in order. We search backwards in time for an @Psy concept-number matching the $seq tag and if we find a match we check its $pos tag for a "6=prep" match, upon which we assign the concept-number to the $prep variable in case we decide to send the designated preposition into the EnPrep() module for inclusion in thinking.

We go back into the code for assigning the $seq tag and in the same line of code we set the $tselp variable falsely and temporarily equal to the $verblock time, so that we may increment the $tselp variable until it becomes true. We insert some code that increments the phony $tselp time by unitary one and uses it to "split" each succeeding conceptual @Psy array row into its fourteen constituent elements, including "$k[1]" which we check for a match with the designated $prep variable. We make several copies of the search-snippet, and it easily finds the $prep engram within just a few time-points of the verb-engram, but now we need to convert the series of search-snippets into a self-terminating loop that will terminate, Arnold, upon finding the prepositional engram in memory. But we have forgotten how to code such a loop in Strawberry Perl Five, so we go into another room of the Mentifex AI Lab and we fetch the books Perl by Example (Quigley) and PERL Black Book (Holzner) to seek some help. We find some sample code for an until loop on page 193 of Quigley. We do not initialize the scalar $tselp at zero, because we are searching for an English preposition quite near to the already-known time-point. For the sake of safety, we insert a line of "last" escape-code in the event that the incrementing $tselp value exceeds the $cns value. The resulting until loop works just fine and it locates the nearby English preposition for us.

Next we insert a warranted call to SpreadAct() into the EnVerbPhrase() module just after the point where Speech() has been called to speak the verb. We wish to set up a routine for spreading activation throughout a prepositional phrase not only after a verb but also after a noun or an adjective (e.g. "young at heart" or an adverb (e.g. "ostensibly at random"). In SpreadAct() we send the $aud tag associated with the located preposition directly into Speech() and the ghost.pl AI starts saying not just "I AM" but "I AM IN". We need to insert more code for finishing the prepositional phrase. By the way, these improvements or mental enhancements are perhaps making the AI Mind capable of much more sophisticated thinking than heretofore. The AI is using words without really knowing what the words mean in terms of sensory perception -- for which robot embodiment is necessary -- but the AI may nevertheless develop self-awareness on top of its innate concept of self or ego. Knowing how to use prepositions, the AI may become curious and ask the human users for all sorts of exploratory information.

Now in SpreadAct() we throw in a call to EnArticle(), even though we have not yet coded in the elocution of the object of the preposition. The AI says "I AM IN A" without stating the object of the preposition. Let us create a new $tselo variable for time of selection of object so that we may use SpreadAct() to zero in on the object and send it into the Speech()module. Finally the ghost.pl AI Mind says "I AM IN A COMPUTER".