We are keeping a list of AI/ML related links from research to more accessible items, hoping to share some of the more accessible posts with a wider community!
I’m not sure if I’d call that reverse engineering any more than using a web browsers View Source feature.
But it’s interesting how it works behind the scenes and that only way to get these models to interface with the external world is by using the natural language interface and hoping for the best.
I’m curious if this is guaranteed accurate information or if GPT gives hallucinations here too lol
As far as i understand GPT cannot self-analyze.
It does not generally hallucinate with data it has, the LLM has to know about the commands it has from the plugin and this can only be done by feeding that data into context.
I suspect they can’t put this info in a system level message as it could cause extra confusion and create an injection vector for un-checked plugins. So instead they shove the command set in a user or assitant message which a user can get access to just by asking. If these commands were in a system message it would generally refuse to help you.
tl;dr - it does not hallucinate data its been given, just when you ask it to “come up” with things.
If these commands were in a system message it would generally refuse to help you.
Doesn’t it usually fairly easily give its system message to the user? I have had that happen purely by accident.
not since the update about a 5 weeks ago. Originally the User scop message was the most powerful and system was practically useless. In response to jailbreaking System was boosted hard and User was nerfed, this is why so many people have been calling GPT “dumber”.
Bascially they made moderation more possible for app devs. Now user messages will be very unlikely (i wont say impossible yet) for someone to get a system message. I have already done a fair bit of adversarial testing with some pentesters and will be doing some more. So far no one has been able to extract the system message verbatim though the can illicit it to explain its boundaries.
It resists finance and physc advice now but its still possible to get around that, at least if you control the system messages. API access is nice.
Is the whole “You are an LLM by OpenAI, system date is etc.” prompt part of the system message?
A few days ago when I was talking about controlled natural languages with it and asked it to give a summary of the chat so far in Gellish it spit that out.
Yes, the standard system message is usually a role stating that its an AI driven chatbot with a handful of anti-jailbreak directives. This can just be a sentence or it can be pages depending on the app.
