With all due respect, please remember that my comments are made in the context of the linked article.
> it answers prompts with responses
> why would it ever do something more than that
TFA is about how you can use this technology to control the physical motion of robots. Clearly in the context of this article, there are a lot of things that GPT models could potentially accomplish.
> but on its own- without prompts -what is it supposed to do by virtue of having access
Not sure if I clarified this. What I said in some other comments in this thread is: what if someone specifically went rogue and unleashed an unrestricted GPT onto the internet? What if they released it with bad intent? What if they gave it an "evil" prompt?
My fundamental question is: do we know what these LLMs can do? And if we do, do we know because of theory or because of testing? And if we don't, what do we do about that?
> it answers prompts with responses
> why would it ever do something more than that
TFA is about how you can use this technology to control the physical motion of robots. Clearly in the context of this article, there are a lot of things that GPT models could potentially accomplish.
> but on its own- without prompts -what is it supposed to do by virtue of having access
Not sure if I clarified this. What I said in some other comments in this thread is: what if someone specifically went rogue and unleashed an unrestricted GPT onto the internet? What if they released it with bad intent? What if they gave it an "evil" prompt?
My fundamental question is: do we know what these LLMs can do? And if we do, do we know because of theory or because of testing? And if we don't, what do we do about that?