4
$\begingroup$

Let's suppose there are two AI boxes, AI_A and AI_B, both of them General Intelligence. Consider that AI_B has the ability to open and modify AI_A. But this action of opening up and modifying is considered BAD by AI_B. Can AI_A ever convince AI_B for this?

$\endgroup$
  • $\begingroup$ Could you please clarify what kind of AI you're talking about? $\endgroup$ – user58 Apr 11 '17 at 17:28
  • $\begingroup$ Well im very new to the concepts behind AI so was hoping others would help clarify that $\endgroup$ – George Deeley Apr 11 '17 at 17:49
  • $\begingroup$ What kind of box? (Hopefully not the same one they had Schrodinger's cat in;) $\endgroup$ – DukeZhou Apr 11 '17 at 22:23
  • 1
    $\begingroup$ Nice joke @DukeZhou XD. This question raises important questions of power relations and independence. I think a great point for AI_A would be that such modifications will destroy diversity. $\endgroup$ – Seth Simba Jan 16 '18 at 9:25
4
$\begingroup$

An AI takes the decision based on the output of their utility function. This is just a fancy word for the calculations that AI perform to compare profit and loss of taking certain decision. I have considered that you are are talking about a General Intelligence. There is always a tight analogy between a General Intelligence and a human. You can juxtapose the utility function to how we take decisions by considering marginal profits of doing something over the other.

Now your question:
The answer is a big NO. This is because an AI (or a human) never takes an action that gives a low score on its utility function or is against the fundamental view of the machine (or human). AI only cares about the utility function and goal state (plus the instrumental goals), nothing else. Our AI outside the box has been created with the purpose of not opening the box. For it, the action of opening the box has a very low score, or a negative score.
Now you might be wondering why an AI can’t be convinced of doing something that gives a low score in its utility function. Keep reading
Consider this for a second. Suppose an AGI (Artificial General Intelligence) was created, assigned with the task of copying the handwriting of others and improving its own writing. You can think of it as a smart writing hand. Now what this AI might come up with is that in order to practice writing it needs more pages and thus it needs to cut more trees for that. No matter what you do, AI will not stop from cutting more and more trees. It might even replicate itself into machines that will cut trees for him. Now, the only thing that can be done is to turn off the AGI. But, a smart machine would have known the possibility of being turned off and thus will have transferred itself to many other machines over the globe. The important question to ask here is, why it is doing all this? It is not because the machine wants to live, as we humans want to. The only reason why it wants to live is to fulfil its goal.
You simply can’t change the fundamental view of the machine. The change can result in, the machine not able to attain its goal or not to that extend (optimal profit). This is the reason why you can’t convince a machine to do something that it was asked not to do as its primary task.
You, as a person, are living a life now, and have some fundamental beliefs. Let us consider that you believe in not killing someone. Now, suppose that I give you a pill and tell you that after taking this pill it will rewire your brain and you will kill first four people you see. But after that you will achieve pure satisfaction and happiness. Now you will definitely not take that pill as it conflicts will something that you believe in now. Also, you will try your best and fight back not to take that pill. The same thing applies to a General Intelligence too. It doesn’t matter what your future version will feel or attain after rewiring of the brain (changes in code), it is what and who you are now matters. This video link will help.

I hope it answers your question. There are lots of things to consider here. I have assumed few things and tried to answer according to that. There is one more thing.
We don’t tell the machines how to do something, instead, we only tell them what to do (at least in the case of AI). This is because sometimes we don’t know the optimal way of solving certain problems. In the case of your question, we don’t know what these two machines will do or say to each other. It will be a very interesting thing to hear or watch.

$\endgroup$
  • $\begingroup$ This does answer my question very well. Thank you for the answer $\endgroup$ – George Deeley Apr 18 '17 at 6:53
  • $\begingroup$ @GeorgeDeeley I am glad I was able to help. Your question was good too. It just needs better wording and need to be more specific for what you are looking for. $\endgroup$ – Ugnes Apr 18 '17 at 9:19
0
$\begingroup$

The types of AI your are referring to are known as Artificial General Intelligence.

Strong, narrow AI has reached important milestones recently, but on AGI, from what I can tell, we aren't even close, and there are fundamental issues no one currently seems to have any idea of how to solve.

Regarding your question, the simple answer is: it depends on which AI is smarter.

(It's more nuanced than that, but right now the question is very general, which is probably apropos;)

I'd recommend reading William Gibson's Neuromancer trilogy if you're interested in AI-in-a-box (it's sort of about that) and also the more recent Quantum Thief Trilogy by Hannu Rajaniemi to get a sense of the mechanics of the issue.

There is a great deal of academic literature on this subject, but it will likely require a little bit of getting up to speed in terms of basic research into the AI field. Future of Life Institute may not be a bad place to start: https://futureoflife.org/background/benefits-risks-of-artificial-intelligence/

$\endgroup$
  • $\begingroup$ Thanks I think this is a great place for me to get started. Much appreciated :) $\endgroup$ – George Deeley Apr 12 '17 at 9:46

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.