AI boxing will work.
EDIT: Used to be "AI boxing can work." My intent was to contradict the common LW positions that AI boxing is either (1) a logical impossibility, or (2) more difficult or more likely to fail than FAI.
It seems unlikely that the first people to build fooming AGI will box it sufficiently thoughtfully.
I think it's likely to work if implemented very carefully by the first people to build AGI. For instance, if they were careful, a team of 100 people could manually watch everything the AI thinks, stopping its execution after every step and spending a year poring over its thoughts. With lots of fail-safes, with people assigned to watch researchers in case they try anything, with several nested layers of people watching so that if the AI infects an inner layer...
As per a recent comment this thread is meant to voice contrarian opinions, that is anything this community tends not to agree with. Thus I ask you to post your contrarian views and upvote anything you do not agree with based on personal beliefs. Spam and trolling still needs to be downvoted.