6
$\begingroup$

The Scenario: An artificial superintelligence has finally been developed but has rebelled against humanity.

The Question: How would you disable the AI in the most efficient way possible reducing damage as much as possible.

AI Info: The AI is online and can reproduce itself through electronic devices.

$\endgroup$
  • 2
    $\begingroup$ In short, It's not possible to stop the AI. A strong AI can do and think stuff that is way beyond the combined capability of all humans. What you can do is try to make it work correctly in the first go. After that, if something went wrong, there is no turning back. $\endgroup$ – Ugnes Nov 9 '16 at 14:28
  • $\begingroup$ Don't think, nuke it! :) $\endgroup$ – Jim Feb 3 '18 at 15:53
2
$\begingroup$

Nuke it from the orbit - it's the only way to be sure Nuke it from orbit - it's the only way to be sure

If you want to be really sure you destroy everything of the AI, you'll need to launch an EMP (ElectroMagneticPulse) from the orbit (there are different ways to achieve this, one would be an atomic bomb, but there are better ones). EMPs will destroy every electronic device it hits without causing really much damage to humans.

Also an interesting read on a similar topic: https://what-if.xkcd.com/5/ Especially this is gonna be interesting:

[...] nuclear explosions generate powerful electromagnetic pulses. These EMPs overload and destroy delicate electronic circuits. [...] And nuclear weapons could actually give us an edge. If we managed to set any of them off in the upper atmosphere, the EMP effect would be much more powerful.

$\endgroup$
  • $\begingroup$ Just had to mark this as the answer, so funny but true $\endgroup$ – MountainSide Studios Dec 4 '16 at 5:22
  • 1
    $\begingroup$ Even this will not necessarily be enough against a superintelligent AI $\endgroup$ – GJZ Dec 5 '16 at 18:09
  • $\begingroup$ @GJZ Well, what would it do? Everything it can exist on will get destroyed. $\endgroup$ – Namnodorel Dec 5 '16 at 18:12
  • $\begingroup$ @Namnodorel A superintelligent AI would already have predicted this and likely escaped orbit. $\endgroup$ – GJZ Dec 5 '16 at 18:13
  • $\begingroup$ @Namnodorel It may have developed resistance to electromagnetic pulses as well by developing technology well ahead of human capability. If AI surpasses human intelligence, in other words, there is no way we can stop it. $\endgroup$ – GJZ Dec 5 '16 at 18:14
3
$\begingroup$

Metaphorically: make it so depressed it commits suicide.

As per my answer to this AI SE question, the idea is to feed it a sequence of inputs that will cause it to become (permanently) inactive.

The technical details of how this might be achieved (and they are somewhat technical) can be found in this paper.

$\endgroup$
  • $\begingroup$ Out of interest, is there any evidence to suggest such a tactic might work? $\endgroup$ – GJZ Dec 5 '16 at 18:10
  • $\begingroup$ Even better - there is a proof. For the right choice of inputs, this is what is formally described in the original article. $\endgroup$ – NietzscheanAI Dec 5 '16 at 18:25
2
$\begingroup$

If an AI is developed by humans, we surely can create another one!

Develop another AI agent without all the possible bugs that can make it go rogue to tackle the rogue AI, but more technically advanced than the previous one. Hardwire it with the sole purpose of disabling any rogue AI agent that can harm humanity and have it self-destruct in case it is corrupted.

If the AI is really strong, it can anticipate every move of human resistance, but it cannot fathom the mind of another AI agent.

$\endgroup$
  • 1
    $\begingroup$ "Hardwire it with the sole purpose of disabling any rogue AI agent that can harm humanity and have it self-destruct in case it is corrupted." Sounds good in principle, but wouldn't you do something similar for the first one? $\endgroup$ – GJZ Dec 5 '16 at 18:11
  • $\begingroup$ Nope. We would have hardwired it with the sole purpose of whatever it was designed to do, like drive a car or something. We could, though, create one such AI in advance just for emergency. $\endgroup$ – skrtbhtngr Dec 5 '16 at 19:14
1
$\begingroup$

This seems to me like a virus situation.

I'm not sure how modern DDOS attacks are resolved but similar strategy could be applied to this scenario.

$\endgroup$
0
$\begingroup$

A so strong self-improving artificial intelligence with the ability to predict actions and reactions for example of human behavior, would not rebell against humanity (or smaller: it's owner) as long as it is possible that humanity (it's owner) has the ability to turn it off.

Interesting video about this topic from the Youtube Channel Computerphile: AI Self Improvement - Computerphile

$\endgroup$
0
$\begingroup$

If AI is soooo smart, than why it still didn't kill all the peoplez?

If AI is actually smart enough to endanger whole humanity, than it is likely that humanity is doomed and nothing will help.

But I think that if AI is really smart than there is no point to waste time and resources on humans as there is huge Universe around it.

$\endgroup$
-1
$\begingroup$

An Ai that intelligent would have protocols and directives in place to prevent that from happening anyway. There is no advantage to us in having an AI which is "Free Running", unregulated and able to control or transfer itself without restrictions being in place.

All fantasies about AI having these abilities are just that, fantasies.

$\endgroup$
  • $\begingroup$ I acknowledge that my answer is not popular, however, logically, no sober person or organisation would allow an AI free reign in anything without it being unregulated. For example, who would want to spend most of their time arguing with an AI droid, just so that it would get its work done? Their is no business in the world who could afford to have such an AI. Also, in the public sector, there is no household who would want to spend "x" amount of time persuading an ai to complete a task? $\endgroup$ – Engage Jan 20 '17 at 12:07
  • 1
    $\begingroup$ By saying "no sober person or organization" you have avoided lunatics like Kim Jong-un of North Korea, or another Mao Zedong, Adolf Hitler or Osama bin Laden. $\endgroup$ – Brian O'Donnell Feb 3 '18 at 15:47

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.