Your browser does not fully support modern features. Please upgrade for a smoother experience.
Submitted Successfully!
Thank you for your contribution! You can also upload a video entry or images related to this topic. For video creation, please contact our Academic Video Service.
Version Summary Created by Modification Content Size Created at Operation
1 handwiki Camila Xu -- 2252 2022-11-15 01:43:51

Video Upload Options

We provide professional Academic Video Service to translate complex research into visually appealing presentations. Would you like to try it?
No, upload directly Yes
Cite
If you have any further questions, please contact Encyclopedia Editorial Office.
HandWiki. AI-Control Problem. Encyclopedia. Available online: https://encyclopedia.pub/entry/34609 (accessed on 25 September 2026).
HandWiki. AI-Control Problem. Encyclopedia. Available at: https://encyclopedia.pub/entry/34609. Accessed September 25, 2026.
HandWiki. "AI-Control Problem" Encyclopedia, https://encyclopedia.pub/entry/34609 (accessed September 25, 2026).
HandWiki. (2022, November 15). AI-Control Problem. In Encyclopedia. https://encyclopedia.pub/entry/34609
HandWiki. "AI-Control Problem." Encyclopedia. Web. 15 November, 2022.
AI-Control Problem
Edit
The content is sourced from: https://handwiki.org/wiki/Philosophy: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. Its study is motivated by the claim that the human race will have to get the control problem right "the first time", as a misprogrammed superintelligence might rationally decide to "take over the world" and refuse to permit its programmers to modify it after launch. In addition, some scholars argue that solutions to the control problem, alongside other advances in "AI safety engineering", might also find applications in existing non-superintelligent AI. Potential strategies include "capability control" (preventing an AI from being able to pursue harmful plans), and "motivational control" (building an AI that wants to be helpful).

artificial intelligence control problem ai-control

References

  1. Bostrom, Nick (2014). Superintelligence (First ed.). ISBN 0199678111. 
  2. "Stephen Hawking: 'Transcendence looks at the implications of artificial intelligence – but are we taking AI seriously enough?'". The Independent (UK). https://www.independent.co.uk/news/science/stephen-hawking-transcendence-looks-at-the-implications-of-artificial-intelligence--but-are-we-taking-ai-seriously-enough-9313474.html. Retrieved 14 June 2016. 
  3. "Stephen Hawking warns artificial intelligence could end mankind". BBC. 2 December 2014. https://www.bbc.com/news/technology-30290540. Retrieved 14 June 2016. 
  4. "Anticipating artificial intelligence". Nature 532 (7600): 413. 26 April 2016. doi:10.1038/532413a. PMID 27121801. http://www.nature.com/news/anticipating-artificial-intelligence-1.19825. Retrieved 14 June 2016. 
  5. "Google developing kill switch for AI". BBC News. 8 June 2016. https://www.bbc.com/news/technology-36472140. Retrieved 12 June 2016. 
  6. "‘Press the big red button': Computer experts want kill switch to stop robots from going rogue". Washington Post. https://www.washingtonpost.com/news/morning-mix/wp/2016/06/09/press-the-big-red-button-computer-experts-want-kill-switch-to-stop-robots-from-going-rogue/. Retrieved 12 June 2016. 
  7. "DeepMind Has Simple Tests That Might Prevent Elon Musk’s AI Apocalypse". Bloomberg.com. 11 December 2017. https://www.bloomberg.com/news/articles/2017-12-11/deepmind-has-simple-tests-that-might-prevent-elon-musk-s-ai-apocalypse. Retrieved 8 January 2018. 
  8. "Alphabet's DeepMind Is Using Games to Discover If Artificial Intelligence Can Break Free and Kill Us All" (in en). Fortune. http://fortune.com/2017/12/12/alphabet-deepmind-ai-safety-musk-games/. Retrieved 8 January 2018. 
  9. "Specifying AI safety problems in simple environments | DeepMind". https://deepmind.com/blog/specifying-ai-safety-problems/. Retrieved 8 January 2018. 
  10. Soares, Nate, et al. "Corrigibility." Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence. 2015.
  11. Orseau, Laurent, and Stuart Armstrong. "Safely Interruptible Agents." Machine Intelligence Research Institute, June 2016.
  12. Chalmers, David (2010). "The singularity: A philosophical analysis". Journal of Consciousness Studies 17 (9–10): 7–65. 
  13. Fallenstein, Benja, and Nate Soares. "Problems of self-reference in self-improving space-time embedded intelligence." Artificial General Intelligence. Springer International Publishing, 2014. 21-32.
  14. Russell, Stuart; Norvig, Peter (2009). "26.3: The Ethics and Risks of Developing Artificial Intelligence". A Modern Approach. Prentice Hall. ISBN 978-0-13-604259-4. 
  15. Dietterich, Thomas; Horvitz, Eric (2015). "Rise of Concerns about AI: Reflections and Directions". Communications of the ACM 58 (10): 38–40. doi:10.1145/2770869. http://research.microsoft.com/en-us/um/people/horvitz/CACM_Oct_2015-VP.pdf. Retrieved 14 June 2016. 
  16. Russell, Stuart (2014). "Of Myths and Moonshine". http://edge.org/conversation/the-myth-of-ai#26015. 
  17. Eliezer Yudkowsky. "Complex value systems in friendly AI." Artificial general intelligence. Springer Berlin Heidelberg, 2011. 388-393.
  18. Kaj Sotala; Roman Yampolskiy (19 December 2014). "Responses to catastrophic AGI risk: a survey". Physica Scripta 90 (1). 
More
©Text is available under the terms and conditions of the Creative Commons-Attribution ShareAlike (CC BY-SA) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
Upload a video for this entry
Information
Subjects: Others
Contributor MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to https://encyclopedia.pub/register :
HandWiki
View Times: 1.7K
Entry Collection: HandWiki
Revision: 1 time (View History)
Update Date: 15 Nov 2022
Table of Contents
    Notice
    You are not a member of the advisory board for this topic. If you want to update advisory board member profile, please contact office@encyclopedia.pub.
    OK
    Confirm
    Only members of the Encyclopedia advisory board for this topic are allowed to note entries. Would you like to become an advisory board member of the Encyclopedia?
    Yes
    No
    ${ textCharacter }/${ maxCharacter }
    Submit
    Cancel
    There is no comment~
    ${ textCharacter }/${ maxCharacter }
    Submit
    Cancel
    ${ selectedItem.replyTextCharacter }/${ selectedItem.replyMaxCharacter }
    Submit
    Cancel
    Confirm
    Are you sure to Delete?
    Yes No
    Academic Video Service
    Feedback