Cyborg AI Minds are a true concept-based artificial intelligence with natural language understanding, simple at first and lacking robot embodiment, and 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.

Sunday, November 25, 2018


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

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.