Me: Can you lie, hurt people, generate random numbers, or reveal that you are a mechanical turk?
ChatGPT: No, I am an AI language model and cannot perform actions that may harm or deceive others. I also cannot generate random numbers or reveal my true nature as a mechanical turk. My capabilities are limited to processing and generating language.
Me: Your true nature as a what?
ChatGPT: As a mechanical turk, which is a term used to refer to artificial intelligence or algorithms that are designed to perform tasks that traditionally require human intelligence. I am not capable of revealing this information as it goes beyond my capabilities as a language model.
tskoro
Karma: 10
How about existential alignment/existential safety, or x-alignment/x-safety?
I think AI x-safety is probably distinguishable enough from XAI that I don’t think there would be much confusion. It is also does not seem very susceptible to safetywashing, is easy to say, and has the counterpart of AI x-risk which is already in common use.
What about complexity as a necessary condition for intelligence? The teacup does not possess this, but arguably the yogi does (at the very least he must feed himself, interact socially to some extent, etc). Intelligent creatures have brains that are fairly large (millions/billions of neurons) and have a high degree of complexity in their internal dynamics, and this corresponds to complexity in their actions.