Skip to main content
157 votes
Accepted

Could a paradox kill an AI?

This classic problem exhibits a basic misunderstanding of what an artificial general intelligence would likely entail. First, consider this programmer's joke: The programmer's wife couldn't take it ...
Robert Cartaino's user avatar
57 votes

Could a paradox kill an AI?

This popular meme originated in the era of 'Good Old Fashioned AI' (GOFAI), when the belief was that intelligence could usefully be defined entirely in terms of logic. The meme seems to rely on the ...
NietzscheanAI's user avatar
28 votes

Could a paradox kill an AI?

I see several good answers, but most are assuming that inferential infinite loop is a thing of the past, only related to logical AI (the famous GOFAI). But it's not. An infinite loop can happen in ...
gaborous's user avatar
  • 476
20 votes

Could a paradox kill an AI?

The halting problem says that it's not possible to determine whether any given algorithm will halt. Therefore, while a machine could conceivably recognize some "traps", it couldn't test arbitrary ...
Ben N's user avatar
  • 2,609
18 votes

Could a paradox kill an AI?

Another similar question might be: "What vulnerabilities does an AI have?" "Kill" may not make as much sense with respect to an AI. What we really want to know is, relative to some goal, in what ways ...
Doxosophoi's user avatar
  • 1,945
11 votes

Could a paradox kill an AI?

Nope in the same way a circular reference on a spreadsheet cannot kill a computer. All loops cyclic dependencies, can be detected (you can always check if a finite Turing machine enters the same state ...
CoffeDeveloper's user avatar
10 votes

Could a paradox kill an AI?

No. This is easily prevented by a number of safety mechanisms that are sure to be present in a well-designed AI system. For example, a timeout could be used. If the AI system is not able to handle ...
intcreator's user avatar
  • 1,335
8 votes

Could a paradox kill an AI?

AIs used in computer games already encounter similar problems, and if well designed, they can avoid it easily. The simplest method to avoid freezing in case of an unsolvable problem is to have a timer ...
vsz's user avatar
  • 180
7 votes
Accepted

What does "death" intuitively mean in the paper "Death and Suicide in Universal Artificial Intelligence"?

The authors do actually give an English definition in terms of the well-known agent formulation of AI: We intend this usage to be intuitive: death means that one sees no more percepts, and takes ...
NietzscheanAI's user avatar
5 votes

Could a paradox kill an AI?

Well, the issue of anthropomorphizing the AI aside, the answer is "yes, sort of." Depending on how the AI is implemented, it's reasonable to say it could get "stuck" trying to resolve a paradox, or ...
mindcrime's user avatar
  • 3,767
4 votes

Could a paradox kill an AI?

It seems to me this is just a probabilistic equation like any other. I'm sure Google handles paradoxical solution sets Billions of times a day, and I can't say my spam filter has ever caused a (ahem) ...
brad sanders's user avatar
4 votes

Could a paradox kill an AI?

Killing AI by 'thinking' about a paradox would be called a bug in implementation of that AI, so it's possible (depending how it's being done), but less likely. Most of AI implementation operate in non-...
kenorb's user avatar
  • 10.5k
3 votes

If mankind can create artificial life in a machine, when would we define it's death?

Death as we know it for natural life is terminal. That is once dead, natural life cannot come back (at least in the current understanding and with current technologies---some people believe otherwise)....
Eric Platon's user avatar
  • 1,510
2 votes

If mankind can create artificial life in a machine, when would we define it's death?

If AI arises from a replicable manufacturing process (e.g. as with modern computers), then it will presumably be possible to take a snapshot of the state of an AI and replicate it without error on ...
NietzscheanAI's user avatar
1 vote

Assuming an AI can die, who manages the state?

The AI agent can be designed in such a way that it could consist of two major components: The free-will component expands the experience of the AI agent and produce outputs based on artificially ...
Ébe Isaac's user avatar
1 vote

Assuming an AI can die, who manages the state?

Following on from your own software verification-based answer to this question, it seems clear that ordinary (i.e. physical), notions of death or imprisonment are not strong enough constraints on an ...
NietzscheanAI's user avatar
1 vote

If mankind can create artificial life in a machine, when would we define it's death?

"Death" exists as a single concept because the underlying reality that it's describing is closely clumped together, and our definition has changed with our ability to change that reality. It seems ...
Matthew Gray's user avatar
  • 4,272

Only top scored, non community-wiki answers of a minimum length are eligible