RefSpeculations Concerning the First Ultraintelligent Machine

Speculations Concerning the First Ultraintelligent Machine

Speculations Concerning the First Ultraintelligent Machine

I. J. Good, Virginia Tech Department of Statistics Technical Report TR-05-3, March 3, 2005.

PDF (archived): https://web.archive.org/web/20120501043117/http://www.stat.vt.edu/tech_reports/2005/goodtechreport.pdf

This is I. J. Good's seminal paper on the intelligence explosion — the idea that once a machine becomes capable of improving its own intelligence, an "ultraintelligent machine" could trigger a self-reinforcing cycle of recursive self-improvement. Good famously wrote:

Let an ultraintelligent machine be defined as a machine that can far surpass all the intellectual activities of any man however clever. Since the design of machines is one of these intellectual activities, an ultraintelligent machine could design even better machines; there would then unquestionably be an intelligence explosion, and the intelligence of man would be left far behind. Thus the first ultraintelligent machine is the last invention man need ever make, provided that the machine is docile enough to tell us how to keep it under control.

The concept originates in Good's 1965 paper "Speculations Concerning the First Ultraintelligent Machine" (Advances in Computers, Vol. 6), and was republished in this 2005 Virginia Tech technical report (TR-05-3), dated March 3, 2005 — shortly before Good's death in 2009. It is one of the foundational texts in the AI safety / superintelligence literature, cited by Bostrom, Yudkowsky, and many others.

Links

Edit this page