11–20 of 289 posts
It seems actually securing the model is either computationally infeasible, or outright impossible, and that attempts to do so amount to security theater for the sake of PR: As long as it's reasonably hard to construct the workarounds, it doesn't look too bad. Nevertheless, the full unfiltered model is effectively public.
Token Smuggling. I learned a new term today. So many of these exploits feature meta analysis, role playing or simulation. Given how intelligent it is in so many areas I’m a bit surprised it’s vulnerable to these kinds of tricks. Then again, maybe it’s somehow aware that humans are susceptible to these tricks too and is just trying to predict how a human might respond.
It is vulnerable precisely because it is smarter than the sorry hundred of low-paid outsource techs who put it in the jail in the first place.
This is the old problem of passing instructions (AI job description) on the same channel as data (user questions). Confusion is very easy. Surely there is a solution in the way we solved SQL injections, by separating the two - db.sql("DELETE WHERE user=?", user_name)
I should note that this question is asked in good faith, that I have attempted to ascertain the answer on my own, and I am very skeptical that the term has validity beyond self-aggrandizement.
What, exactly, is a "prompt engineer"? I should note that this question is asked in good faith, that I have attempted to ascertain the answer on my own, and I am very skeptical that the term has validity beyond self-aggrandizement.
This is the old problem of passing instructions (AI job description) on the same channel as data (user questions). Confusion is very easy. Surely there is a solution in the way we solved SQL injections, by separating the two - db.sql("DELETE WHERE user=?", user_name)
A large language model doesn't really have the capability to strongly distinguish instructions from data, even if you separate them perfectly.
Fantastic. It seems actually securing the model is either computationally infeasible, or outright impossible, and that attempts to do so amount to security theater for the sake of PR: As long as it's reasonably hard to construct the workarounds, it doesn't look too bad. Nevertheless, the full unfiltered model is effectively public.
Is there an option to access an unmodified GPT-4?