The interesting questions are whether we could invent a containment area which didn't include clues that it was a simulation, and if the AI deduces that it's in a simulation, whether it could find a way out.
So: that is why there are so few clues that we are being simulated!
Many people think you can solve the Friendly AI problem just by writing certain failsafe rules into the superintelligent machine's programming, like Asimov's Three Laws of Robotics. I thought the rebuttal to this was in "Basic AI Drives" or one of Yudkowsky's major articles, but after skimming them, I haven't found it. Where are the arguments concerning this suggestion?