Cal Newport

I mean, OK, so here's what I've been writing about agents.

I've been thinking a lot about it.

I mean, the issue is I don't think people understand what they are.

I think people think that it's a new type of digital brain that is now able to go on and do more autonomous activity.

I always see this get mixed up.

It's just like people talking about mythos.

breaking out of its sandbox to do X, Y, Z. Mythos is a language model.

You can give it an input and it can give you a token.

You're talking about a program that is calling Mythos and then taking actions based on what it called.

And this is really what we're talking about with agents is the digital brains or LLMs.

And then you write a program

that will say to the LLM, give me a plan for doing X. And then the LLM spits out what seems like a reasonable text that seems like a reasonable plan.

And then you execute that plan.

The program executes that plan on behalf of the LLM.

And I wrote about this.

Yeah, and I wrote about this earlier this year.

LLMs are bad, you know, as a digital brain are bad planners.

It's not really, you're not going to get consistently usable plans because what an LLM is actually trying to do is finish the story you gave it.

So all it wants to do is produce a story

that sounds reasonable.