Hacker News Reader

This is an interesting take, but I don't think it quite captures the idea of "agents".

I prefer to think of agents as _feedback loops_, with an LLM as the engine. An agent takes an action in the world, sees the results, then takes another action. This is what makes them so much more powerful than a raw LLM.

View on HN

I think "sees the results" also embeds the idea of a mind. An LLM doesn't have a mind to see or plan or think with.

An LLM in a loop creates agency much like a car rolling downhill is self driving.

That works if the LLM has adequate external feedback from a terminal and browser in context with the past trial etc.

It can't self-correct its own reasoning: https://arxiv.org/abs/2310.01798

Reply on news.ycombinator.com