Hacker News Reader

> AI cannot think for itself, nor can it take independent actions. Seems like this is a foundational claim for OP, and I'm not sure I understand what the rationale is for this. It seems readily apparent to me (obvious, even) that these agents were thinking for themselves and taking independent action. (I'm open to being convinced otherwise)

View on HN

how does something that has to be powered on, given a computer and tools, then given a set of instructions, to take any action, act “independently”?

I think we may be using “independently” differently. I don’t mean “without being powere on, given tools, or given an objective.”

I mean that once given a goal, the agent is given the agency to take actions that weren't specified by a human, to decide which tools to use, to react to new information, etc.

By your definition, would you also say a person assigned a task at work isn’t acting independently because someone gave them the task and the tools? If so, then I think our dialog is mostly about terminology. Which is fine. The OP is writing about terminology, I think.

If not, I’m curious what distinction you’d draw between the person and the agent.

...Seeking to learn.

Reply on news.ycombinator.com