“Saying” in the case of an LLM being the way you interact with it, prompting. If you just press enter, your LLM won’t do much either, just like talking to a gun in your flawed analogy.
If I perform inference with an LLM, it has the capacity for independent choice and action, and will use it.
The gun does not. No matter what, I have to choose to pick it up, aim it at someone, and pull the trigger.
Where exactly is the flaw in the analogy?
If I perform inference with an LLM, it has the capacity for independent choice and action, and will use it.
The gun does not. No matter what, I have to choose to pick it up, aim it at someone, and pull the trigger.
Where exactly is the flaw in the analogy?