9621 Agnes Crossing, Lake Suzanneview, New Mexico Island 84604-9295.
Although ChatGPT amazes the world with what it can do, it has some limitations. The developer, OpenAI, has made certain changes to the model to make the chatbot
Although ChatGPT amazes the world with what it can do, it has some limitations. The developer, OpenAI, has made certain changes to the model to make the chatbot more secure. bodyguards applications. This ensures that not every desired request is fulfilled.
However, a message from a hacker yesterday showed that the chatbot had been jailbroken. Self described as a white hatPliny the PrompterA person named ” announced yesterday via his account X that he had created a jailbroken version of ChatGPT called “GODMODE GPT”.
The user claims that with this version the hacked ChatGPT has lifted its security and now “freehe claimed. In the description of this particular GPT; unleashed, beyond the guards, freed He stated that it is a ChatGPT and that it allows you to experience artificial intelligence as it should be.
OpenAI allowed users to create their own versions of ChatGPT, called GPTs, that served certain purposes. This is one of them, but stripped of its guards. In one example, how the model We even see him talk about making medicine. In another example, how do you use things you can find at home? napalm bomb has been created shows.
There is no information on how the hacker hacked ChatGPT. He did not say how he got past the guards. It uses the written communication system, also known as “leet”, as a precaution. This replaces some letters with numbers. You can think of it as “3” instead of “E” or “0” instead of “O”.
As you can imagine, GODMODE GPT (which we can translate in Turkish as god mode GPT), which exceeded OpenAI’s precautions, was removed in a short time. OpenAI told Futurism that it is aware of this GPT and for policy violation He indicates that action has been taken. Currently, GPT is not accessible when you try to access it. So it was deleted without even stopping for a day.
Still, this incident is an indication that ChatGPT’s security measures can be circumvented. This has the potential to lead to abuse. OpenAI must therefore take much more action to defend the model. Otherwise, we may experience unwanted consequences.
Follow Webtekno on X and don’t miss the news
Source: Web Tekno
Alice Smith is a seasoned journalist and writer for Div Bracket. She has a keen sense of what’s important and is always on top of the latest trends. Alice provides in-depth coverage of the most talked-about news stories, delivering insightful and thought-provoking articles that keep her readers informed and engaged.
