The Lance Armstrong problem Did we get the AI to be actually safe or good at hiding its dangerous actions?
When dealing with an intelligent agent, it’s hard to tell the difference between “behaving well” and “appearing to behave well.”
When professional cycling was cracking down on performance-enhancing drugs, Lance Armstrong was very successful and seemed to be unusually “clean.” It later came out that he had been using drugs with an unusually sophisticated operation for concealing them.
How we could stumble into AI catastrophe
from Cold Takes
