Hacker News new | ask | show | jobs
by int_19h 1200 days ago
It's not clear whether a generic solution is even possible.

In a sense, this is the same problem as, "how do I trust a person to not screw up and do something against instructions?" And the answer is, you can minimize the probability of that through training, but it never becomes so unlikely as to disregard it. Which is why we have things like hardwired fail-safes in heavy machinery etc.