Mike Cafarella

Well, if that was the goal, like mission accomplished. More good books out of it than anyone else. So yeah, sure.

Well, if that was the goal, like mission accomplished. More good books out of it than anyone else. So yeah, sure.

but I think we're ready to get going.

but I think we're ready to get going.

Yeah, exactly. That's it.

Yeah, exactly. That's it.

All right. So one year, I'm... a little bit chagrined by last year's prediction for one year, which imagined a cyberpunk future in an unreasonable 12-month time span. That's probably not going to happen. So I want to make it a little more modest.

All right. So one year, I'm... a little bit chagrined by last year's prediction for one year, which imagined a cyberpunk future in an unreasonable 12-month time span. That's probably not going to happen. So I want to make it a little more modest.

I'm going to take the opposite side of Simon's and say that the strong agent vision is as ludicrous as everyone says, but weak agents, some weak version of this kind of squishy thing, is actually here to stay, by which I mean inference time, like, post-LLM inference procedures to improve or to have a whole sequence of LLM requests. I think that's actually going to be around for a long time.

I'm going to take the opposite side of Simon's and say that the strong agent vision is as ludicrous as everyone says, but weak agents, some weak version of this kind of squishy thing, is actually here to stay, by which I mean inference time, like, post-LLM inference procedures to improve or to have a whole sequence of LLM requests. I think that's actually going to be around for a long time.

And it means that like previous LLM interactions that were a little bit lengthy, a little bit annoying, but basically okay, are now going to stretch to minutes long.

And it means that like previous LLM interactions that were a little bit lengthy, a little bit annoying, but basically okay, are now going to stretch to minutes long.

So I totally agree. Calling it an agent is insane. Letting it have arbitrary, it's like a software module that has no expected termination time. And no like budget of anything. Anyway, that is crazy. But some of the agent programming frameworks exist basically to chain optional sequence. Like, hey, I'm going to I'm going to write some code on your behalf. Then I'm going to try to lint it.

So I totally agree. Calling it an agent is insane. Letting it have arbitrary, it's like a software module that has no expected termination time. And no like budget of anything. Anyway, that is crazy. But some of the agent programming frameworks exist basically to chain optional sequence. Like, hey, I'm going to I'm going to write some code on your behalf. Then I'm going to try to lint it.

And if the linting fails, then I'm going to rewrite the prompt.

And if the linting fails, then I'm going to rewrite the prompt.

So, you know, I agree it's been around like in real world examples for some time, but I think in the last year we saw a kind of abstraction of that pattern for the first time. Totally, yeah. That they call mixture of agents, which I hate the name, but like the basic idea is that you farm it out to...

So, you know, I agree it's been around like in real world examples for some time, but I think in the last year we saw a kind of abstraction of that pattern for the first time. Totally, yeah. That they call mixture of agents, which I hate the name, but like the basic idea is that you farm it out to...

either 10 different models or the same model with very high temperature settings, you get multiple candidate answers and then you try to integrate them. It definitely does better on some tasks, right?

either 10 different models or the same model with very high temperature settings, you get multiple candidate answers and then you try to integrate them. It definitely does better on some tasks, right?