[mystifyingpoi]

Oh, they are. It's just that the harness around it is able to pick up the commands it "autocompletes" and runs them for you. LLM can't run anything, it never could.

[fl7305]

What do you mean that the "harness ran the commands"?

It looks to me like the LLM "executed" the logic in pure output tokens, not by using any kind of external tool calls?

[mystifyingpoi]

Right, I mean that the logic of creating the packet was in the output tokens, sure. But the actual sending of the packet was done by bash command.

[fl7305]

Sure, we agree there.

But it seems to me that if the LLM can effectively "execute" the instruction of how to take an input IP packet and generate a response IP packet based on a set or rules, then that's effectively a general purpose processor. And not an "auto completer", right?

[mystifyingpoi]

That's one way to look at it, but you're right - taking "autocompletion" to the extreme, we arrived at a task executor.

[fl7305]

To me, "autocompletion" means a pure lookup function input->output.

That's a lot different from "general purpose processor which can act based on program logic, stored data, and input data".