Back to LessWrong

Orthogonality thesis

From Lesswrongwiki

Revision as of 03:49, 14 October 2016 by Ete (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search
Arbital has an article about

The orthogonality thesis states that an artificial intelligence can have any combination of intelligence level and goal. This is in contrast to the belief that, because of their intelligence, AIs will all converge to a common goal. The thesis was originally defined by Nick Bostrom in the paper "Superintelligent Will", (along with the instrumental convergence thesis). For his purposes Bostrom defines intelligence to be instrumental rationality.

Defense of the thesis

It has been pointed out that the orthogonality thesis is the default position, and that the burden of proof is on claims that limit possible AIs. Stuart Armstrong writes that,

Thus to deny the Orthogonality thesis is to assert that there is a goal system G, such that, among other things:

  1. There cannot exist any efficient real-world algorithm with goal G.
  2. If a being with arbitrarily high resources, intelligence, time and goal G, were to try design an efficient real-world algorithm with the same goal, it must fail.
  3. If a human society were highly motivated to design an efficient real-world algorithm with goal G, and were given a million years to do so along with huge amounts of resources, training and knowledge about AI, it must fail.
  4. If a high-resource human society were highly motivated to achieve the goals of G, then it could not do so (here the human society is seen as the algorithm).
  5. Same as above, for any hypothetical alien societies.
  6. There cannot exist any pattern of reinforcement learning that would train a highly efficient real-world intelligence to follow the goal G.
  7. There cannot exist any evolutionary or environmental pressures that would evolving highly efficient real world intelligences to follow goal G.

One reason many researchers assume superintelligences to converge to the same goals may be because most humans have similar values. Furthermore, many philosophies hold that there is a rationally correct morality, which implies that a sufficiently rational AI will acquire this morality and begin to act according to it. Armstrong points out that for formalizations of AI such as AIXI and Gödel machines, the thesis is known to be true. Furthermore, if the thesis was false, then Oracle AIs would be impossible to build, and all sufficiently intelligent AIs would be impossible to control.

Pathological Cases

There are some pairings of intelligence and goals which cannot exist. For instance, an AI may have the goal of using as little resources as possible, or simply of being as unintelligent as possible. These goals will inherently limit degree of intelligence of the AI.

Blog posts

See also

External links