AI Boxing is attempts, experiments, or proposals to isolate (“box”) an unaligned AI where it can’t interact with the world at large and cause harm. See also: AI
Challenges are: 1) can you successively prevent it from interacting with the world? And 2) can you prevent it from convincing you to let it out?
from the original talk page
Talk:AI boxing
If an SF reference is not considered a faux pas, this reminds me of John Barnes ( https://en.wikipedia.org/wiki/John_Barnes_%28author%29 ) “Meme Wars”. The way One True infected humanity is, if possible, an obvious attack vector for a sufficiently powerful AI. -- Resuna (talk) 10:20, 27 November 2014 (AEDT)