But during inference, when you’re actually talking to Claude or GPT-4, the system is frozen. It processes your input, generates a response, and… that’s it. The prediction errors it’s implicitly computing don’t modify anything that persists as “the system.” There’s no absorption into durable structure.
It’s worth pointing out that the weights being fixed doesn’t mean everything is fixed. The LLM can react in-context, it just can’t modify other instances of itself.
Good point, poor choice of words on my part. I meant for example:
UserMessage: Hello GPTMessage: Hello! How may I assist you? UserMessage: I need directions to the mall.
Is actually something like
A = [“Hello”], B = [“Hello”, “Hello! How may I assist you?”, “I need directions to the mall”]
And if you send A to the model with the same params you’ll get the same probability distribution back for every trial. (Same actual response for temperature==0, in practice mostly the same response for temperature >0). Ditto for B. The context is not independent but the model responses are independent of each other.
It’s worth pointing out that the weights being fixed doesn’t mean everything is fixed. The LLM can react in-context, it just can’t modify other instances of itself.
Well, it’s deterministic, right? The reaction is preordained
Aren’t human reactions deterministic too though? I’m not sure I understand what you’re arguing.
Good point, poor choice of words on my part. I meant for example:
UserMessage: Hello
GPTMessage: Hello! How may I assist you?
UserMessage: I need directions to the mall.
Is actually something like
A = [“Hello”], B = [“Hello”, “Hello! How may I assist you?”, “I need directions to the mall”]
And if you send A to the model with the same params you’ll get the same probability distribution back for every trial. (Same actual response for temperature==0, in practice mostly the same response for temperature >0). Ditto for B. The context is not independent but the model responses are independent of each other.