Stuart_Armstrong comments on [LINK] Concrete problems in AI safety - Less Wrong
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (6)
In software, it's trivial: create a subroutine with only a very specific output, include the entity inside it. Some precautions are then needed to prevent the entity from hacking out through hardware weaknesses, but that should be doable (using isolation in faraday cage if needed).