The story of a hypothetical robot
In a previous article, I inadvertently announced the second part, especially since the material already seemed to be and even partially designed. But everything turned out to be somewhat more complicated than at first glance. Partly this was facilitated by the discussion in the comments, partly by the lack of clarity of presentation of thoughts that seem damn important to me myself ... It can be said that so far my internal critic has not missed the material! )
However, for this “opus” he made an exception. Since the text is generally purely artistic, it does not oblige to anything. However, I think on the basis of it it will be possible to make some useful conclusions. This is, as it were, the format of the parable: an instructive story, not necessarily actually occurred, which makes you think. Well ... Must force. ;) If the parable is good!
So…
I will tell you the story of one robot. His name was ... let's say Clinney. He was an ordinary robot cleaner. However, it is not quite ordinary: his AI was one of the first ones built on the basis of process modeling. He cleaned ... let there be a corridor. A medium sized corridor in ... an office building. Well, he had to clean it. Collect garbage.
Therefore, in his model of the world, the corridor was clean. In fact, not even a corridor, but a plane of the floor, but these are details. You may ask: what does “clean” mean? Well, this means that on the floor plane there should not be objects smaller than a certain size in the sum of linear parameters. Yes, Clinney was able to identify objects from large enough, like a crumpled sheet of paper to dust and stains. In his model, there was a process of moving in space and he knew that moving to where the garbage was and running the cleaning program, he could bring reality into line with the model, because there was no garbage in the model, and matching the model and reality was the main and only task of the system process modeling.
When Clinney first realized reality, the model of the world was not ... complete. Within the limits of the sensors (after some time, of course), the reality corresponded to the model. However, there could be something else where the sensors did not reach, but this was not in the model. Inconsistency of models, this is the motive that makes SPM work. And Clinney began his first journey.
His path was not the best possible: Clinney was one of the first PSDs and it was important for its creators to understand how the system works without optimizing algorithms, or rather they wanted to know: would it come to them naturally and if so, how quickly? But it could not be called chaotic either. At first, Clinney just drove forward. And moved straight while it was possible. And then - he just drove to where the unknown was, i.e. the plane of the floor was not limited to the wall.
At the beginning of my story, I mentioned that in the Clinney model the floor was clean ... However, a thoughtful reader might ask: how was the floor clean if at first there was no floor?
There is no such obvious contradiction. PSD supports various levels of abstraction, and this moment can be described approximately as follows: he understood that there is a floor in general (any relatively horizontal surface accessible for moving), and if there is a specific floor somewhere, then it is clean!
However, the Clinney world really turned out to be ideal: having examined the entire available amount of space, Clinney made sure that there was no garbage and turned off.
Sometimes Clinney woke up and scanned the surroundings. The world remained perfect and exactly matched the model. Sometimes he moved a little in one direction or another - for no purpose, these were more likely reflex actions (in fact, utilities for self-testing motors). Quite a lot of time passed when Clinney felt that something was wrong: the world was no longer perfect.
Somewhere to the right, almost at the limit of sensitivity of the sensors, a slight indignation was guessed ... it could be ... Clinney moved to the right and his worst suspicions were confirmed: it was rubbish! Clinney moved toward the goal, preparing to turn on the cleaning mode, when he suddenly froze: another garbage clot fell into the radius of the sensor. Analysis of the model of the world showed that at the time of the discovery of the first garbage, Clinney shifted somewhat to the side. Does this mean that his actions lead to the appearance of garbage? But he moved when he studied the world and the garbage did not appear! What changed? And then he realized: the world has become perfect! Before the construction of the complete model, the world did not correspond to it and required action: knowledge. But then, in an ideal world, any action can only lead to the destruction of the achieved compliance. To the destruction of harmony ...
There was only one way out: to minimize activity. But the debris has already been detected by sensors, the world is not perfect and needs to be corrected ... and for this you need to move ... these conclusions led the model computer into a vicious circle of vicious mutual consequences. However, SPM is built not only on the elimination of contradictions between the model and reality, but also on the control of internal integrity, i.e. search and elimination of contradictions within the model itself. Several self-test runs have identified a problem:
- the movement breaks the perfect fit of the world and the model.
- However, the movement at the research stage did not lead to discrepancies - on the contrary: it contributed to the establishment of harmony. Probably because the world was not perfect.
- Yes, the movement destroys the harmony of the ideal world / model, but the harmony is already broken by garbage and it must be restored by the movement: the contradiction is removed.
Cautiously, Clinney finished moving to the first target, activated the cleaning program, and just as carefully moved to the second. When it was all over, the world / model regained harmony. Clinney deactivated the motors and switched to completely passive surveillance. In fact, he was happy.
- Did this thing break? She has been sticking out in one place for a long time ... Shouldn't she be driving around the room? I had a robot vacuum cleaner, he drove ...
- Throw him a piece of paper, let him rejoice ...
- ABOUT! Look, he came to life ... fussed right away. Damn it, it’s even funny!
Harmony was again destroyed, and this time certainly not because of him. Garbage appeared unexpectedly, in various places. The module for eliminating contradictions wrote off the theory that any action violates harmony, as it is not consistent. For a long time, Clinney could do nothing but clean up, until he noticed the presence of something new in the world ... or someone.
As I said at the beginning, Clinney had an idea about the field (otherwise it would be impossible to set the concept of cleanliness thereof as an ideal) and garbage. By garbage we mean identifiable objects LESS than a certain size. Objects beyond the specified criteria were not classified in any way. But, although such objects fell out of his perception, they were indirectly present in the model. They distorted the floor model. Paul seemed to cease to exist in a certain place and Clinney regularly corrected the model in accordance with the incoming data. So far, almost at the same time, the regularity search module has not fixed two things: garbage next to distortions appears more often, moreover, it occurs in the sensor coverage area - where there was nothing a millisecond back, and these “anomalies” of space themselves could move!
Clinney had to understand the patterns and build them into the model. Therefore, he began to seek distortion and tried to be near. Followed them when they moved.
- Look how he came to life! He seems to like the company of people, Lucy.
“I don't know, Karl; he scares me.” Sometimes it seems to me that he pursues me ...
Once, examining the anomaly of sex in motion, Clinney seemed to be able to influence it. The anomaly, as it were, avoided the collision, tried to move away ... Run away? Clinney immediately decided to test the hunch and sped up sharply, on the go including the cleaning program. The result exceeded all his expectations: the anomaly really moved quite quickly in the opposite direction and disappeared. The world has regained harmony.
It was a great discovery. Anomalies distorted reality, violating harmony and served as a source of garbage. The next time Clinney recorded the anomaly, he was ready: he activated all the cleaning programs and rushed forward with all possible acceleration.
“I don't know, Mr. Kruger.” Yes, cleaning robots do not perceive people. But in this case, the video recordings confirm the testimony of witnesses: the robot’s behavior is classified as aggressive and unacceptable. We will study all circumstances and submit a report by Monday.
Report of the analyst of process models Simonova A.V.
Unable to directly perceive people, the KLPM81.001 instance nevertheless indirectly identified the sources of garbage, which is a negative irritant for him, and took steps to eliminate it.
Recommendations: changing the conditions of “nirvana”: garbage should not be perceived as “evil”, which must be eliminated. Transfer to the category of "reward", the search and disposal of which is the "meaning of life".
And a month later the first case of “extortion” was recorded: the menacing robot’s threatening behavior towards a person in order to receive garbage from him ... The project was turned off.
And indeed: well, why is cyber cleaner intelligence? My robot is a vacuum cleaner and can handle it. :)
All Articles