Tiling Agents for Self-Modifying AI , and the Löbian Obstacle *

  title={Tiling Agents for Self-Modifying AI , and the L{\"o}bian Obstacle *},
  author={Eliezer and Herreshoff},
We model self-modification in AI by introducing “tiling” agents whose decision systems will approve the construction of highly similar agents, creating a repeating pattern (including similarity of the offspring’s goals). Constructing a formalism in the most straightforward way produces a Gödelian difficulty, the “Löbian obstacle.” By technical methods we demonstrate the possibility of avoiding this obstacle, but the underlying puzzles of rational coherence are thus only partially addressed. We… CONTINUE READING
Highly Cited
This paper has 23 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
16 Extracted Citations
26 Extracted References
Similar Papers

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 26 references

A Comparison of Decision Algorithms on Newcomblike Problems.” http://intelligence.org/files/Comparison.pdf

  • Altair, Alex
  • 2013

An Angle of Attack on Open Problem #1.

  • Fallenstein, Benja
  • Less Wrong (blog), August 18
  • 2012

Open Problems in Friendly Artificial Intelligence.

  • Yudkowsky, Eliezer
  • Paper presented at Singularity Summit
  • 2011

Similar Papers

Loading similar papers…