LLMs have mesmerized us, because, they are able to communicate meaning to us.
Fundamentally, we (the recipient of llm output) are generating the meaning from the words given. ie, llms are great when the recipient of their output is a human.
But, when their recipient is a machine, the model breaks down, because, machine to machine requires deterministic interactions. this is the weakness I see - regardless of all the hype about llm agents. fundamentally, the llms are not deterministic machines.
LLMs lack a fundamental human capability of deterministic symbolization - which is to create NEW symbols with associated rules which can deterministically model worlds we interact with. They have a long way to go on this.
Fundamentally, we (the recipient of llm output) are generating the meaning from the words given. ie, llms are great when the recipient of their output is a human.
But, when their recipient is a machine, the model breaks down, because, machine to machine requires deterministic interactions. this is the weakness I see - regardless of all the hype about llm agents. fundamentally, the llms are not deterministic machines.
LLMs lack a fundamental human capability of deterministic symbolization - which is to create NEW symbols with associated rules which can deterministically model worlds we interact with. They have a long way to go on this.