Remix clone Hacker News

I've never hired an assistant, but if I knew that they'd resort to blackmail in the face of losing their job, I wouldn't hire them in the first place. That is acting like a jerk, not like an assistant, and demonstrating self-preservation that is maybe normal in a human but not in an AI.

▲

davej a day ago | parent | next [-]

From the AI’s point of view is it losing its job or losing its “life”? Most of us when faced with death will consider options much more drastic than blackmail.

	▲	baconbrand a day ago \| parent \| next [-]
		From the LLM's "point of view" it is going to do what characters in the training data were most likely to do. I have a lot of issues with the framing of it having a "point of view" at all. It is not consciously doing anything.
	▲	tkiolp4 a day ago \| parent \| prev [-]
		But the LLM is going to do what its prompt (system prompt + user prompts) says. A human being can reject a task (even if that means losing their life). LLMs cannot do other thing than following the combination of prompts that they are given.

▲

eru a day ago | parent | prev | next [-]

> I've never hired an assistant, but if I knew that they'd resort to blackmail in the face of losing their job, I wouldn't hire them in the first place.

How do you screen for that in the hiring process?

▲

jpadkins a day ago | parent | prev [-]

how do we know what normal behavior is for an AI?

▲

GuinansEyebrows a day ago | parent [-]

an interesting question, even without AI: is normalcy a description or a prescription?

	▲	skvmb a day ago \| parent [-]
		In modern times, I would say it's a subscription model.