AI boxing

From Lesswrongwiki
Revision as of 11:01, 30 June 2012 by TerminalAwareness (talk | contribs) (First draft)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

It has often been proposed that as long as an AGI is physically and otherwise isolated, or boxed, it can do little harm. However, since an AGI may be far smarter than any person interacting with it, the AGI may be able to influence any user to let them out of their "box", and human control.

AI Boxing is often discussed in the context of Oracle AI, but not exclusively.

A number of strategies for boxing are discussed in Thinking inside the box. Among them are:

  • Physical Security
  • No Manipulators
  • Limiting the AI’s output
  • Periodic resets of the AI's memory
  • An interface between the real world and the AI where it would reveal its unfriendly intentions first
  • Motivational control, using a variety of techniques

Both Eliezer Yudkowsky and Justin Corwin have ran simulations, pretending to be a superintelligence, and been able to convince a human playing a guard to let them out on many - but not all - occasions. These experiments have used a set of arbitrary rules,

References

Thinking inside the box: using and controlling an Oracle AI by Stuart Armstrong, Anders Sandberg, and Nick Bostrom on the Difficulty of AI Boxing by paulfchristiano http://lesswrong.com/lw/3cz/cryptographic_boxes_for_unfriendly_ai/ by paulfchristiano

= See Also

The Experiments