OpenAI’s viral chatbot ChatGPT continues to surprise us with its answers. We can place the artificial intelligence robot in different roles and we can even get answers from it within the scope of this role. Agree, A virtual world managed by ChatGPT what would it look like?

The answer to this question was provided by researchers from Stanford University and Google. Scientists left 25 virtual characters under the control of ChatGPT. each lived in a virtual world for a day. Oddly enough, no chaotic situation was observed in the resulting results.

Goal “convincing simulations of human behavior”, Visual depictions of conversations between characters. In this world, the characters do not move physically, only the text and events develop.

Each of the 25 characters ChatGPT checked had its own personality and identity. These characters include characters such as John and John’s son Eddy, all chats between characters are produced and developed by ChatGPT. For example, the character of John was described to him as:

Each character’s event stream also begins with similar inputs. ChatGPT is then asked to determine what the next step will be. The next move is written by ChatGPT and this cycle continues.

In a scenario where John is told to wake up at 8 AM, ChatGPT first has John brush his teeth, kiss his wife, dress her, and take her to the kitchen. Simultaneously with John’s storyline, his son Eddy’s plot is being developed. Eddy gets up, brushes his teeth and goes to the kitchen.

With the two in the same environment, namely in the kitchen, the experimental infrastructure that followed the ChatGPT event also tells that there is another character in the environment where one character is. When the following action is requested, a conversation like this can arise:

The time of day is also advanced by ChatGPT after each action, with the estimated time of that action. Commands like these are sent to the characters after each action:

• Response from ChatGPT: Hi Eddy, how’s your musical composition project going for your class?

The day ends with these mentions being given to each character. Currently, only positive human responses have been received in the simulations.

So what will this research do for us?

The answer to this question lies in the introductory sentence of the scientists’ research: “Credible representations of human behavior can enable interactive applications ranging from immersive environments to exercise rooms and prototyping tools for interpersonal communication.”

In other words, the development of such technologies, both in real life and in the virtual world. interactions between humans and artificial intelligence can reach a more realistic level. Examples include conversations that develop completely naturally while playing a game like The Sims, and actually chatting with your smart devices.