Uh. I read your question again and have to clarify. It's due to the structure that you're not seeing. Behind the scenes for a model trained for chat, there are

Uh. I read your question again and have to clarify. It's due to the structure that you're not seeing. Behind the scenes for a model trained for chat, there are demarcations like: <|im_start|>Do dogs have four legs?<|im_end|> <|assistant|> See that the model is now primed to further generate as the assistant because it's fine-tuned to be a completion engine that adheres to this format. If we didn't encode this information behind the scenes, yes absolutely you will see the output you described. You can even see it for yourself with raw models from earlier generations. You need to give the LLM an idea of what you want and you provide this idea by formatting your document correctly using structure like above. Let's say you wanted JSON output explicitly without any explanation. Put words into the mouth of the assistant itself and it will continue. <|assistant|>```json { The structure above will force the model to continue on that trajectory. You can also ask ChatGPT: "please start your next sentence with Ok, I'll pretend to be a human"