Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [control-problem]

For question related to the "AI control problem".

In artificial intelligence (AI) and philosophy, the AI control problem is the hypothetical puzzle of how to build a superintelligent agent that will aid its creators, and avoid inadvertently building a superintelligence that will harm its creators.

https://en.wikipedia.org/wiki/AI_control_problem

27 questions
12
votes
4 answers

Is overfitting always a bad thing?

DNN can be used to recognize pictures. Great. For that usage, it's better if they are somewhat flexible so as to recognize as cats even cats that are not on the pictures on which they trained (i.e. avoid overfitting). Agreed. But when one uses NN as…
ZakC
  • 347
  • 2
  • 7
10
votes
3 answers

What's the term for death by dissolving in AI?

What's the term (if such exists) for merging with AI (e.g. via neural lace) and becoming so diluted (e.g. 1:10000) that it effectively results in a death of the original self? It's not quite "digital ascension", because that way it would still be…
ikaruss
  • 211
  • 1
  • 4
9
votes
6 answers

Would an AI with human intelligence have the same rights as a human under current legal frameworks?

For example, would an AI be able to own property, evict tenants, acquire debt, employ, vote, or marry? What are the legal structures in place to implement a strong AI into society?
fuzzyhedge
  • 245
  • 1
  • 7
6
votes
3 answers

What would be the best way to disable a rogue AI?

Suppose that an artificial superintelligence (ASI) has finally been developed, but it has rebelled against humanity. We can assume that the ASI is online and can reproduce itself through electronic devices. How would you disable the AI in the most…
MountainSide Studios
  • 353
  • 1
  • 9
4
votes
1 answer

Why is GLIE Monte-Carlo control an on-policy control?

In slide 16 of his lecture 5 of the course "Reinforcement Learning", David Silver introduced GLIE Monte-Carlo Control. But why is it an on-policy control? The sampling follows a policy $\pi$ while improvement follows an $\epsilon$-greedy policy, so…
fish_tree
  • 247
  • 1
  • 6
4
votes
3 answers

Is there a way to protect humanity against the impending singularity?

We are careening into the future which may hold unpredictable dangers in relation to AI. I've haven't yet heard of Chappie or Robocop style police robots, but militarized drone tech is replacing many conventional weapons platforms. I love the idea…
GIA
  • 568
  • 6
  • 22
4
votes
2 answers

Which government agencies oversee development of new AI?

Nick Bostrom talks in his book Superintelligence about the many dangers of AI. He considers it necessary that strong security mechanisms are put in place to ensure that a machine, once it gains general intelligence far beyond human capabilities,…
Demento
  • 1,684
  • 1
  • 7
  • 26
4
votes
1 answer

Could artificial intelligence cause problems for humanity after figuring out human behavior?

This BBC article suggests that intelligent algorithms, like those that select news stories and advertisements for display, could control our experience of the world and manipulate us. Will Artificial Intelligence someday become a problem to humanity…
quintumnia
  • 1,183
  • 1
  • 10
  • 34
4
votes
2 answers

What AI concept is behind the Mars Exploration Rover (MER)?

The Mars Exploration Rover (MER) Opportunity landed on Mars on January 25, 2004. The rover was originally designed for a 90 Sol mission (a Sol, one Martian day, is slightly longer than an Earth day at 24 hours and 37 minutes). Its mission has been…
Abhishek T.
  • 141
  • 1
  • 1
  • 6
4
votes
1 answer

Can the AI in a box experiment be formalized?

Introduction The AI in a box experiment is about a super strong game AI which starts with lower resources than the opponent and the question is, if the AI is able to win the game at the end, which is equal to escape from the prison. A typical…
user11571
3
votes
1 answer

Is learning possible without random thoughts and actions?

In my view intelligence begins once the thoughts/actions are logical rather than purely randomn based. The learning environments can be random but the logic seems to obey some elusive rules. There is also the aspect of a parenting that guides…
dankilev
  • 143
  • 7
3
votes
1 answer

What is the Control Problem?

The Wikipedia page describes AI control problem in very intricated way. Therefore I would like to better understand it based on some simple explanation, what's going on. Basically I don't want any copy & pastes from wiki, because the articles there…
kenorb
  • 10,423
  • 3
  • 43
  • 91
3
votes
2 answers

Is policy learning and online system identification the same?

In some newer robotics literature, the term system identification is used in a certain meaning. The idea is not to use a fixed model, but to create the model on the fly. So it is equal to a model-free system identification. Perhaps a short remark…
user11571
2
votes
1 answer

Are linear approximators better suited to some tasks compared to complex neural net functions?

Model based RL attempts to learn a function $f(s_{t+1}|s_t, a_t)$ representing the environment transitions, otherwise known as a model of the system. I see linear functions are still being used in model-based RL such as in robotic manipulation to…
mugoh
  • 531
  • 4
  • 20
2
votes
1 answer

Neural networks with internal dynamics in the state-space form

Neural networks with feedback (Hopfield, Hamming, etc.) differ from ordinary neural networks (multilayer perceptrons, etc.), which turns them into a dynamic element with its own internal dynamics (if we consider them as a separate dynamic link). The…
dtn
  • 227
  • 1
  • 6
1
2