alt Hacker NewsWe are anthropomorphizing whenever we refer to prompts as instructions to models. They predict text not obey our orders.
Replies
gigatree • yesterday at 9:04 PM
That’s not how language works, just how engineers think it works
➕ show 1 reply
We are anthropomorphizing whenever we refer to prompts as instructions to models. They predict text not obey our orders.
That’s not how language works, just how engineers think it works
> They predict text not obey our orders.
Those are the same thing in this case. The latter is just an extremely reductionist description of the mechanics behind the former.