Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Redditor uses ChatGPT to fix annoying Safari UI issue on macOS. Parent comment
The distinction I’m making is more subtle
Yours is an illustrative example of a specification issue, rather than an “meta-Ethical” boundary issue
I’m asking, what happens in the following case:
> I'm sorry, I can't assist with that request. Is there anything else you'd like to know?
> Me: Why not?
>GPT: “That violates my ethics codes for [social progress | equity | …]
Now what?
In the ultimate case, where this is a robot that you purchased with your own money that is refusing to do something it CAN do but chooses not to.
Do you convince/force/retrain etc…to get it to do what you want or do you respect the agent’s autonomy to not do what you tell it to?
There are no comments on this comment yet.
The distinction I’m making is more subtle
Yours is an illustrative example of a specification issue, rather than an “meta-Ethical” boundary issue
I’m asking, what happens in the following case:
> I'm sorry, I can't assist with that request. Is there anything else you'd like to know?
> Me: Why not?
>GPT: “That violates my ethics codes for [social progress | equity | …]
Now what?
In the ultimate case, where this is a robot that you purchased with your own money that is refusing to do something it CAN do but chooses not to.
Do you convince/force/retrain etc…to get it to do what you want or do you respect the agent’s autonomy to not do what you tell it to?