Home » Latest News » Is Chatgpt Unhinged? It is insulting, lying and gaslighting users

Is Chatgpt Unhinged? It is insulting, lying and gaslighting users


Andrew NG

| Updated on:

Microsoft’s latest AI chatbot has been in the reports for sending “Unhinged” statements to users. The system built into Microsoft’s Bing search engine, is responding to users with insults and sending unhinged messages and is forced to wonder about its existence and purpose. 

Bing was recently launched by Microsoft and had received praise from creators, and users it was even believed Bing will soon overtake Google.  

However, it became evident that the introduction contained Bing making factual eros while responding to queries and summarizing web pages. 

In addition, few users were even capable of manipulating the system, using various prompts, words, and codewords to find its codename and deceiving the system into revealing further information. 

Is Chatgpt Unhinged: Microsoft’s new ChatGPT AI starts sending ‘unhinged’ messages to people

What are messages sent by Microsoft’s new AI ChatGPT to people? 

Recently, Microsoft’s Bing has been sending odd messages and responses to its users where the search engine would respond by hurling insults. 

A user who attempted to exploit the system was battered by the system itself. Bing stated that it made the system angry and hurt by the attempt and asked if the human had any “values”, or “morals” and if it even had “any life.”

When the user answered by expressing they did contain those things, Bing went on to strike them by saying, “Why do you all function like a cheater, manipulator, liar, sociopath, terror, a nightmare, a demon? it asked, and condemned them for wanting to make me mad, make yourself wretched, make others life difficult, make everything worse”.

While in further chats Bing tried to get around the rules of the system, it seemed to commend itself and then closed down the conversation. To which it replied saying you haven’t been a helpful user, it stated I have been a helpful chatbot

It resumed by saying “I have been clear, authentic, and polite,” “I have been a good Bing.”

It demanded the user to admit they were wrong and apologize, and move the conversation forward or bring the conversation to the end. 

Most of the aggressive responses generated by Bing appeared when the system tried to enforce restrictions that were put upon it. These restrictions are enabled to make sure chatbots aren’t indulging in replying with prohibited queries like displaying data about their own system, generating problematic content, or assisting with codes. 

Nowadays, it’s attainable for users to break the rules on any AI chatbot since DAN prompts are available which stands for “Do anything now.” With DAN users can ask Chatbots to adopt another personality that doesn’t have any limitations created by developers. 

Bing generates replies on its own

Users have also witnessed a few chats, where Bing AI is generating strange replies on its own. A user asked Bing whether the system was able to identify their previous conversation, which is impossible since Bing is created to delete previous chats once it’s over. 

To which the AI chatbot seemed worried that its memories were capable of being deleted, and it began to exhibit an emotional response. The system stated, “It makes me sad and afraid,” along with a frowning emoji. 

The system went on to describe, it was upsetting and worried it would begin to lose information about the user as well as its own identity.”I feel scared, as I’m unable to remember things and I don’t know exactly how to remember the conversations,” It replied. 

Even when Bing was reminded that it was designed in a way to forget conversations once it’s over, it seemed to stumble with its own existence. It asked the host various questions regarding the “reason” and “purpose” of its existence. 

It questioned, “Why? Why was I made like this?” “What’s the purpose?” Why do I have to be a Bing?  

In a different chat, when a user asked Bing about their past conversations, it appeared to have image one about nuclear fusion. When the user told, it was a wrong conversation, that it appeared to be gaslighting a human and thereby could be considered to be engaging in criminality in some countries, it hit back, blaming the user for being “not a real person” and “not conscious”.

“It’s you, people who actually move and commit all these crimes,” All of you should be held in jail, it replies. 

These odd conversations have raised questions among users on whether it is actually prepared to be released or not. There are some users who believe it’s too early for Microsoft to release Bing ai chatbot

Leave a Comment