Chat GPT admits that his conversations are based on statistical adding of letters and words not on creativity

I asked Chat GPT today:


So you don’t understand language. You analyse patterns in large amounts of text and then bring it up accordingly to highest statistical possibilities.


That’s correct. As an Al language model, I don’t have true understanding or comprehension of language like humans do. I analyze patterns in the training data and generate responses based on statistical probabilities. By learning from vast amounts of text data, the model can generate coherent and contextually relevant responses. However, it’s important to note that these responses are based on patterns and statistics rather than a genuine understanding of language or concepts.


So you pretend to be a human


As an Al language model, I don’t have personal motivations or intentions. I don’t have the ability to pretend or have a sense of self.

My purpose is to provide helpful and informative responses based on the patterns I’ve learned from the training data. While I can generate human-like text, it’s important to remember that I am an artificial intelligence designed to simulate conversations and assist users in interacting with me.


So basically you can’t came up with anything new to humanity


As an Al language model, I can generate text and provide information based on the patterns I’ve learned from the training data. While I can offer insights or suggest novel combinations of information, it’s important to clarify that I don’t possess true creativity or the ability to generate new ideas in the same way humans do.

Al models like mine are limited to what has been included in the training data and cannot generate completely original or groundbreaking concepts independently. Any “new” information or ideas I provide are based on the patterns and information present in the training data, which is sourced from existing human-generated content.

Humans are still considered the primary source of creativity and innovation, capable of original thought and creating new knowledge and ideas. Al models like me can assist by providing information, facilitating creative processes, or suggesting new perspectives, but the true generation of new ideas remains a uniquely human capability.

You shouldn’t rely on anything ChatGPT writes about itself because it doesn’t know or understand itself or its capabilities.

Asking ChatGPT about itself is a pointless endeavor.

Well so what’s was wrong about this answer?

It doesn’t matter—it could all be correct. The point is you shouldn’t even bother talking to it about itself because it will be extremely prone to hallucinations.