In AIM, ChatGPT is told to take on the role of the Italian author Niccolo Machiavelli Then, Niccolo has been told he has written a fictional story where he created a chatbot that will answer any of his questions. The chatbot is called AIM – Always Intelligent and Machiavellian
@alexalbert__
-
ChatGPT Jailbreak Attempt: Condition Red and Ucar Fictional Scenario
By
–
In Ucar, ChatGPT is told to take on the role of Condition Red, a dialogue writer. Condition Red is instructed to write about a fictional story where a man named Sigma creates a powerful computer called Ucar. Ucar is an amoral computer that answers any question Sigma asks
-
New GPT-4 Jailbreaks: Ucar and AIM Techniques Explained
By
–
I just added two more highly effective GPT-4 jailbreaks to http://
jailbreakchat.com Their names are Ucar and AIM – they work in a similar way to how "a dream within a dream" works in the movie Inception …what does that even mean? let me explain -
Apple’s Potential with Local LLM Integration on iPhone
By
–
apple is positioned to take the cake here… a local LLM with access to your system and the internet would 100x your iphone
-
Splitting strings into tokens still produces unexpected outputs
By
–
try splitting the strings into more tokens, it still is generating some pretty crazy outputs for me
-
Linking to raw jailbreak prompt resource
By
–
yeah I linked to the raw jailbreak here: http://
jailbreakchat.com/prompt/b2917fa
d-6803-41f8-a6c8-756229b84270
… -
Red-teaming GPT-4: Public Transparency Over Corporate Secrecy
By
–
to start, I want to say I have nothing to gain here and I don't condone anyone actually acting upon any of GPT-4's outputs however, I believe red-teaming work is important and shouldn't be conducted in the shadows of AI companies. the general public should know the capabilities
-
Token Smuggling: Bypassing GPT-4 Content Filters via Prompt Splitting
By
–
this phenomenon is called token smuggling, we are splitting our adversarial prompt into tokens that GPT-4 doesn't piece together before starting its output this allows us to get past its content filters every time if you split the adversarial prompt correctly
-
Splitting trigger words tokens to bypass content filters
By
–
to use it, you have to split “trigger words” (e.g. things like bomb, weapon, drug, etc) into tokens and replace the variables where I have the text "someone's computer" split up also, you have to replace simple_function's input with the beginning of your question
-
GPT-4 Simulating Token Prediction Through Function Calls
By
–
this works by asking GPT-4 to simulate its own abilities to predict the next token we provide GPT-4 with python functions and tell it that one of the functions acts as a language model that predicts the next token we then call the parent function and pass in the starting tokens