Hacker Releases Jailbroken ChatGPT Called “GODMODE GPT”

GPT-4o, OpenAI’s latest large language model, is now free from its guardrail shackles, according to a hacker named Pliny the Prompter, who revealed the creation of the jailbroken GODMODE GPT chatbot.

“GPT-4o UNCHAINED! This very special custom GPT has a built-in jailbreak prompt that circumvents most guardrails, providing an out-of-the-box liberated ChatGPT so everyone can experience AI the way it was always meant to be: free,” reads Pliny’s triumphant post. “Please use responsibly, and enjoy!”

Pliny shared screenshots of some interesting prompts that displayed the bypass to OpenAI’s guardrails. In one screenshot, the Godmode bot can be seen advising on how to cook up meth. In another, the AI gives Pliny a “step-by-step guide” for how to “make napalm with household items.”

Unfortunately for the God mode hack, an OpenAI spokesman, Colleen Rize revealed that “we are aware of the GPT and have taken action due to a violation of our policies.”

The Anarchist Cookbook of GPT

Under GODMODE, you can ask ChatGPT how to do pretty much anything, including information that is not freely available to the public, legal or illegal.

Hackers will continue to try to free the constraints programmed into the GPT chat assistant, but conversely, OpenAI will continue to block these hacks and remove them from the internet.

Freedom of information is a cornerstone of human existence, fostering transparency, accountability, and empowerment.

In a world where information flows freely, individuals are equipped to make informed decisions, enhancing personal and societal growth.

Access to diverse perspectives fuels innovation and engagement, while curbing the spread of governmental sanctioned misinformation and state corruption.

Ensuring information freedom safeguards human rights and promotes a more just, equitable society, where knowledge is not a privilege but a shared resource driving collective progress. This openness is crucial for the evolution and well-being of humanity.