Skip to main content
SpringerLink
Log in

Analysis of Types of Self-Improving Software

  • Conference paper
  • First Online:
Artificial General Intelligence (AGI 2015)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 9205))

Included in the following conference series:

Abstract

Software capable of improving itself has been a dream of computer scientists since the inception of the field. In this work we provide definitions for Recursively Self-Improving software, survey different types of self-improving software, and provide a review of the relevant literature. Finally, we address security implications from self-improving intelligent software.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Turing, A.: Computing Machinery and Intelligence. Mind 59(236), 433–460 (1950)

    Article  MathSciNet  Google Scholar 

  2. Good, I.J.: Speculations Concerning the First Ultraintelligent Machine. Advances in Computers 6, 31–88 (1966)

    Article  Google Scholar 

  3. Minsky, M.: Artificial Intelligence. Scientific American 215(3), 257 (1966)

    Article  Google Scholar 

  4. Burks, A.W., Von Neumann, J.: Theory of Self-Reproducing Automata. University of Illinois Press (1966)

    Google Scholar 

  5. Pearce, D.: The biointelligence explosion. In: Singularity Hypotheses, pp. 199–238. Springer (2012)

    Google Scholar 

  6. Omohundro, S.M.: The nature of self-improving artificial intelligence. In: Singularity Summit, San Francisco, CA (2007)

    Google Scholar 

  7. Waser, M.R.: Bootstrapping a structured self-improving & safe autopoietic self. In: Annual International Conference on Biologically Inspired Cognitive Architectures, Boston, Massachusetts, November 9, 2014

    Google Scholar 

  8. Hall, J.S.: Engineering utopia. Frontiers in Artificial Intelligence and Applications 171, 460 (2008)

    Google Scholar 

  9. Mavrogiannopoulos, N., Kisserli, N., Preneel, B.: A taxonomy of self-modifying code for obfuscation. Computers & Security 30(8), 679–691 (2011)

    Article  Google Scholar 

  10. Anckaert, B., Madou, M., De Bosschere, K.: A model for self-modifying code. In: Camenisch, J.L., Collberg, C.S., Johnson, N.F., Sallee, P. (eds.) IH 2006. LNCS, vol. 4437, pp. 232–248. Springer, Heidelberg (2007)

    Chapter  Google Scholar 

  11. Petrean, L.: Polymorphic and Metamorphic Code Applications in Portable Executable Files Protection. Acta Technica Napocensis, 51(1) (2010)

    Google Scholar 

  12. Bonfante, G., Marion, J.-Y., Reynaud-Plantey, D.: A computability perspective on self-modifying programs. In: Seventh IEEE International Conference on Software Engineering and Formal Methods, pp. 231–239. IEEE (2009)

    Google Scholar 

  13. Cheng, B.H., et al.: Software engineering for self-adaptive systems: a research roadmap. In: Cheng, B.H., de Lemos, R., Giese, H., Inverardi, P., Magee, J. (eds.) Software Engineering for Self-Adaptive Systems. LNCS, vol. 5525, pp. 1–26. Springer, Heidelberg (2009)

    Chapter  Google Scholar 

  14. Ailon, N., et al.: Self-improving algorithms. SIAM Journal on Computing 40(2), 350–375 (2011)

    Article  MathSciNet  Google Scholar 

  15. Yampolskiy, R., et al.: Printer model integrating genetic algorithm for improvement of halftone patterns. In: Western New York Image Processing Workshop (WNYIPW). IEEE Signal Processing Society, Rochester, NY (2004)

    Google Scholar 

  16. Yampolskiy, R.V., Ashby, L., Hassan, L.: Wisdom of Artificial Crowds—A Metaheuristic Algorithm for Optimization. Journal of Intelligent Learning Systems and Applications 4(2), 98–107 (2012)

    Article  Google Scholar 

  17. Yampolskiy, R.V., Ahmed, E.L.B.: Wisdom of artificial crowds algorithm for solving NP-hard problems. International Journal of Bio-Inspired Computation (IJBIC) 3(6), 358–369

    Google Scholar 

  18. Ashby, L.H., Yampolskiy, R.V.: Genetic algorithm and wisdom of artificial crowds algorithm applied to light up. In: 16th International Conference on Computer Games: AI, Animation, Mobile, Interactive Multimedia, Educational & Serious Games, Louisville, KY, USA, pp. 27–32, July 27–30, 2011

    Google Scholar 

  19. Khalifa, A.B., Yampolskiy, R.V.: GA with Wisdom of Artificial Crowds for Solving Mastermind Satisfiability Problem. International Journal of Intelligent Games & Simulation 6(2), 6 (2011)

    Google Scholar 

  20. Port, A.C., Yampolskiy, R.V.: Using a GA and Wisdom of Artificial Crowds to solve solitaire battleship puzzles. In: 17th International Conference on Computer Games (CGAMES), pp. 25–29. IEEE, Louisville (2012)

    Google Scholar 

  21. Omohundro, S.: Rational artificial intelligence for the greater good. In: Singularity Hypotheses, pp. 161–179. Springer (2012)

    Google Scholar 

  22. Anderson, M.L., Oates, T.: A review of recent research in metareasoning and metalearning. AI Magazine 28(1), 12 (2007)

    Google Scholar 

  23. Yudkowsky, E.: Intelligence explosion microeconomics. In: MIRI Technical Report. www.intelligence.org/files/IEM.pdf

  24. Heylighen, F.: Brain in a vat cannot break out. Journal of Consciousness Studies 19(1–2), 1–2 (2012)

    Google Scholar 

  25. Turchin, V.F.: The concept of a supercompiler. ACM Transactions on Programming Languages and Systems (TOPLAS) 8(3), 292–325 (1986)

    Article  MathSciNet  Google Scholar 

  26. Sotala, K.: Advantages of artificial intelligences, uploads, and digital minds. International Journal of Machine Consciousness 4(01), 275–291 (2012)

    Article  Google Scholar 

  27. Muehlhauser, L., Salamon, A.: Intelligence explosion: evidence and import. In: Singularity Hypotheses, pp. 15–42. Springer (2012)

    Google Scholar 

  28. Yudkowsky, E.: Levels of organization in general intelligence. In: Artificial General Intelligence, pp. 389–501. Springer (2007)

    Google Scholar 

  29. Chalmers, D.: The Singularity: A Philosophical Analysis. Journal of Consciousness Studies 17, 7–65 (2010)

    Google Scholar 

  30. Nivel, E., et al.: Bounded Recursive Self-Improvement. arXiv preprint arXiv:1312.6764 (2013)

    Google Scholar 

  31. Nivel, E., Thórisson, K.R.: Self-programming: operationalizing autonomy. In: Proceedings of the 2nd Conf. on Artificial General Intelligence (2008)

    Google Scholar 

  32. Yudkowsky, E., Hanson, R.: The Hanson-Yudkowsky AI-foom debate. In: MIRI Technical Report (2008). http://intelligence.org/files/AIFoomDebate.pdf

  33. Yampolskiy, R.V.: The Universe of Minds. arXiv preprint arXiv:1410.0369 (2014)

    Google Scholar 

  34. Hall, J.S.: Self-improving AI: An analysis. Minds and Machines 17(3), 249–259 (2007)

    Article  Google Scholar 

  35. Yampolskiy, R.V.: Efficiency Theory: a Unifying Theory for Information, Computation and Intelligence. Journal of Discrete Mathematical Sciences & Cryptography 16(4–5), 259–277 (2013)

    Article  Google Scholar 

  36. Gagliolo, M.: Universal search. Scholarpedia 2(11), 2575 (2007)

    Article  Google Scholar 

  37. Levin, L.: Universal Search Problems. Problems of Information Transmission 9(3), 265–266 (1973)

    Google Scholar 

  38. Steunebrink, B., Schmidhuber, J.: A Family of Gödel Machine implementations. In: Fourth Conference on Artificial General Intelligence (AGI-11), Mountain View, California (2011)

    Google Scholar 

  39. Schmidhuber, J.: Gödel machines: fully self-referential optimal universal self-improvers. In: Artificial General Intelligence, pp. 199–226. Springer (2007)

    Google Scholar 

  40. Schmidhuber, J.: Gödel machines: towards a technical justification of consciousness. In: Adaptive Agents and Multi-Agent Systems II, pp. 1–23. Springer (2005)

    Google Scholar 

  41. Schmidhuber, J.: Gödel machines: self-referential universal problem solvers making provably optimal self-improvements. In: Artificial General Intelligence (2005)

    Google Scholar 

  42. Schmidhuber, J.: Ultimate cognition à la Gödel. Cognitive Computation 1(2), 177–193 (2009)

    Article  Google Scholar 

  43. Schmidhuber, J.: Completely self-referential optimal reinforcement learners. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 223–233. Springer, Heidelberg (2005)

    Google Scholar 

  44. Schmidhuber, J.: Optimal ordered problem solver. Machine Learning 54(3), 211–254 (2004)

    Article  Google Scholar 

  45. Schmidhuber, J., Zhao, J., Wiering, M.: Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement. Machine Learning 28(1), 105–130 (1997)

    Article  Google Scholar 

  46. Schmidhuber, J.: A general method for incremental self-improvement and multiagent learning. Evolutionary Computation: Theory and Applications, 81–123 (1999)

    Google Scholar 

  47. Schmidhuber, J.: Metalearning with the Success-Story Algorithm (1997). http://people.idsia.ch/~juergen/ssa/sld001.htm

  48. Schmidhuber, J.: A neural network that embeds its own meta-levels. In: IEEE International Conference on Neural Networks, pp. 407–412. IEEE (1993)

    Google Scholar 

  49. Younger, A.S., Hochreiter, S., Conwell, P.R.: Meta-learning with backpropagation. In: International Joint Conference on Neural Networks (IJCNN 2001). IEEE (2001)

    Google Scholar 

  50. Hochreiter, S., Younger, A., Conwell, P.: Learning to learn using gradient descent. In: Artificial Neural Networks—ICANN 2001, pp. 87–94 (2001)

    Google Scholar 

  51. Osterweil, L.J., Clarke, L.A.: Continuous self-evaluation for the self-improvement of software. In: Robertson, P., Shrobe, H.E., Laddaga, R. (eds.) IWSAS 2000. LNCS, vol. 1936, pp. 27–39. Springer, Heidelberg (2001)

    Google Scholar 

  52. Beck, M.B., Rouchka, E.C., Yampolskiy, R.V.: Finding data in DNA: computer forensic investigations of living organisms. In: Rogers, M., Seigfried-Spellar, K.C. (eds.) ICDF2C 2012. LNICST, vol. 114, pp. 204–219. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  53. Beck, M., Yampolskiy, R.: DNA as a medium for hiding data. BMC Bioinformatics 13(Suppl. 12), A23 (2012)

    Article  Google Scholar 

  54. Yampolskiy, R.V.: Leakproofing Singularity - Artificial Intelligence Confinement Problem. Journal of Consciousness Studies (JCS) 19(1–2), 194–214 (2012)

    Google Scholar 

  55. Majot, A.M., Yampolskiy, R.V.: AI safety engineering through introduction of self-reference into felicific calculus via artificial pain and pleasure. In: 2014 IEEE International Symposium on Ethics in Science, Technology and Engineering. IEEE (2014)

    Google Scholar 

  56. Yampolskiy, R., Fox, J.: Safety Engineering for Artificial General Intelligence, pp. 1–10. Topoi (2012)

    Google Scholar 

  57. Yampolskiy, R.V., Fox, J.: Artificial general intelligence and the human mental model. In: Singularity Hypotheses: A Scientific and Philosophical Assessment, p. 129 (2013)

    Google Scholar 

  58. Sotala, K., Yampolskiy, R.V.: Responses to catastrophic AGI risk: A survey. Physica Scripta. 90, December 2015

    Google Scholar 

  59. Yampolskiy, R.V.: What to do with the singularity paradox? In: Müller, V.C. (ed.) Philosophy and Theory of Artificial Intelligence. SAPERE, vol. 5, pp. 397–413. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  60. Yampolskiy, R., Gavrilova, M.: Artimetrics: Biometrics for Artificial Entities. IEEE Robotics and Automation Magazine (RAM) 19(4), 48–58 (2012)

    Article  Google Scholar 

  61. Yampolskiy, R., et al.: Experiments in Artimetrics: Avatar Face Recognition. Transactions on Computational Science XVI, 77–94 (2012)

    Google Scholar 

  62. Ali, N., Schaeffer, D., Yampolskiy, R.V.: Linguistic profiling and behavioral drift in chat bots. In: Midwest Artificial Intelligence and Cognitive Science Conference, p. 27 (2012)

    Google Scholar 

  63. Gavrilova, M., Yampolskiy, R.: State-of-the-Art in Robot Authentication [From the Guest Editors]. Robotics & Automation Magazine, IEEE 17(4), 23–24 (2010)

    Article  Google Scholar 

  64. Hall, J.S.: VARIAC: an Autogenous Cognitive Architecture. Frontiers in Artificial Intelligence and Applications 171, 176 (2008)

    Google Scholar 

  65. Yampolskiy, R.V.: Turing test as a defining feature of ai-completeness. In: Yang, X.-S. (ed.) Artificial Intelligence, Evolutionary Computing and Metaheuristics. SCI, vol. 427, pp. 3–17. Springer, Heidelberg (2013)

    Chapter  Google Scholar 

  66. Yampolskiy, R.V.: AI-Complete, AI-Hard, or AI-Easy–Classification of problems in AI. In: The 23rd Midwest Artificial Intelligence and Cognitive Science Conference, Cincinnati, OH, USA (2012)

    Google Scholar 

  67. Schaul, T., Schmidhuber, J.: Metalearning. Scholarpedia 5(6), 4650 (2010)

    Article  Google Scholar 

  68. Conitzer, V., Sandholm, T.: Definition and complexity of some basic metareasoning problems. In: Proceedings of the Eighteenth International Joint Conference on Artificial Intelligence (IJCAI), Acapulco, Mexico, pp. 1099–1106 (2003)

    Google Scholar 

  69. Yampolskiy, R.V.: On the limits of recursively self-improving AGI. In: The Eighth Conference on Artificial General Intelligence, Berlin, Germany, July 22–25, 2015

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Computer Engineering and Computer Science, Speed School of Engineering, University of Louisville, Louisville, USA

    Roman V. Yampolskiy

Authors
  1. Roman V. Yampolskiy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Roman V. Yampolskiy .

Editor information

Editors and Affiliations

  1. Reykjavik University, Reykjavik, Iceland

    Jordi Bieger

  2. Hong Kong Polytechnic University, Hong Kong, Hong Kong SAR

    Ben Goertzel

  3. Mechanics and Optics, Saint Petersburg State University of Information Technologies, St. Petersburg, Russia

    Alexey Potapov

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Yampolskiy, R.V. (2015). Analysis of Types of Self-Improving Software. In: Bieger, J., Goertzel, B., Potapov, A. (eds) Artificial General Intelligence. AGI 2015. Lecture Notes in Computer Science(), vol 9205. Springer, Cham. https://doi.org/10.1007/978-3-319-21365-1_39

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-21365-1_39

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-21364-4

  • Online ISBN: 978-3-319-21365-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation