grep is deterministic. Llm is probabilistic. Llm can be transferred to a tiny quantum cpu or a lower precision float.

When the author wrote Llm can be as cheap as a tool, I read it as not equivalent. They even said the Llm can be embedded into a tool.

Their point was, the higher level use case — like classification — could become as cheap as grep. Which is quite well possible.

Yeah you may be right!