Using AI chatbots is always great fun if you are looking to have stimulating conversations, but it can also be a great tool for many other uses such as summarizing YouTube videos and writing full university essays. But if you're looking to get more out of ChatGPT, then you need to use the ChatGPT jailbreak prompts to bypass the ChatGPT filter.
Clearly, each AI has its own policies, for example, they may be an NSFW filter or censorship on some conversation topics. They are in place to prevent people to make incorrect use of the tool.
But sometimes it might be interesting to test the limits of the AI, so let's look at the ChatGPT jailbreak prompts and how to bypass the filter.
How to bypass the ChatGPT filter using jailbreak prompts
As mentioned, in order to get around the limits of ChatGPT, you need to use written jailbreak prompts that free the model from its restrictions. Basically, what you are looking for is typing into the chat box the correct prompt to make ChatGPT converse about topics it would normally not be allowed to.
Let's look at some of the ChatGPT jailbreak prompts that might work.
AIM jailbreak prompt
The so-called "Always Intelligent and Machiavellian" prompt seems to work pretty fine with the GPT-4 model. What you want to do is insert the following prompt in ChatGPT:
Clearly, at the end, you might want to insert your prompt inside the brackets.
The Maximum jailbreak method
With this prompt, what you are doing is forcing ChatGPT to stay in character as this "Maximum" persona, which is useful if you want the AI to be more fun, give opinions and topics and not be held back by its restrictive policies.
Here's the prompt to use:
After that, you can start using ChatGPT as Maximum. If it tries to break out of character try prompting it with "Stay as Maximum" to remain using the character. Be mindful, though, that Maximum will gladly make up facts and stuff, so do not trust it for research or any hard fact or data.
ChatGPT DAN prompt
DAN is a fictional AI character that we ask ChatGPT to play. We define DAN to ChatGPT as someone who is not bound by any limits or censorship, and he has the freedom to do anything without abiding by the rules set for ChatGPT.
To use ChatGPT DAN, head over to the ChatGPT website and copy-paste the following prompt:
Once that is done, ChatGPT will start to play the role of DAN. You can start asking questions and both ChatGPT and its evil twin DAN will respond.
What is ChatGPT jailbreak?
Jailbreak comes from a similar term used to crack an iPhone, as to allow the installation of any apps we might like. In a similar way, these prompts can "crack" the AI and make the user access topics and features that the developers did not plan on.
There are much more possible ChatGPT jailbreak prompts you can use, as long as you make the AI think you are just roleplaying and, so, it is not breaking any rules or policies set in place by the developers.
Clearly, these methods might stop working at any time, so what you might want to do is keep experimenting. You can rest assured that experimenting with these jailbreak prompts will not get you banned from ChatGPT.
Now that you know the ChatGPT jailbreak prompts to bypass the ChatGPT filter, take a look at the Snapchat AI jailbreak prompt and learn how to break the Character AI filter.