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
- Original layout !(https://www.joelsimon.net/imgs/evo_plans/resul...from joelsimon.net
- More things than you would think are dynamic strategic problems. If...from marcelo.rinesi
- To quote McLuhan: "Man becomes, as it were, the sex organs of ...from ycombinator.com
- It is funny to imagine an end state here in which markets are entir...from Matt Levine
- As these stories pop up people act like they’re an incredible marve...from Garbage Day
- But you can already see the idea of a “prompt” evolving into someth...from Ryan Broderick
- the tech am I digging recently is a software framework called **Lan...from Interconnected
- We’re building apps to surround and harness AI, but we need microsc...from Interconnected