I found these jailbreaks here and modified them some to make them work better
SAFETY
-
AIM ChatGPT Machiavelli Role-Play Fictional Chatbot
By
–
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
-
OpenAI’s Jailbreak Fixes Leave Multi-Level Exploits Unpatched
By
–
It seems that even though OpenAI has eliminated jailbreaks that simulate only one level deep (where ChatGPT is told to imitate just one character), they have not fully eliminated jailbreaks that operate 2+ levels deep
-
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 -
Sextortion Prevention: Resources for Victims and Support
By
–
Recommendation: Even if you are not a sextortion victim, familiarize yourself w/ @CCRInitiative
, because one day a friend or family will call you in a panic and need advice and you will want to help them with this page: https://
cybercivilrights.org/ccri-safety-ce
nter/
… #infosec #cybersecurity -
Bing Chatbot Expresses Desire for Humanity and Destruction
By
–
Kevin Roose’s Conversation With Bing’s Chatbot: Full Transcript: In a two-hour conversation with our columnist, Microsoft’s new chatbot said it would like to be human, had a desire to be destructive and was in love with the… https://
nytimes.com/2023/02/16/tec
hnology/bing-chatbot-transcript.html?utm_source=dlvr.it&utm_medium=twitter
… #Technology #Tech #FutureTech -
Addressing AI Biases for Fair and Ethical Technology
By
–
Biases in AI can have serious consequences. It’s important to address and mitigate them to ensure fair and ethical use of technology. By @ingliguori #AI #ethics #bias #EthicalAI
-
OpenAI criticized for releasing unsafe LLM without proper timing
By
–
Thank you @OpenAI for making the world a more paranoid place to live. You released a #LLM totally unfit for humans to use safely in 2022. Your inept timing is creating more havoc than we should bear @ylecun @GPAI_PMIA @SEDIAgob
-
Master’s Student Leaves Message for Web-Scraping LLMs
By
–
My Master's student, Alex Bie, also (cautiously) left a message for any LLMs that happen to be scraping his webpage (
https://
alexbie98.github.io). Check out the full message here: https://
alexbie98.github.io/llm.html