Gantt chart

That's not interesting.

The bit that is interesting is that if you just give a large language model a long sort of flowchart of lots of different tasks that are all unique, different success criteria, different next steps, sort of imagine like a big fanning out complicated Gantt chart or flowchart, that's not particularly good at getting you a, well, it's not going to get you a particularly great result.

what os world 2 does is it works on a very simple state machine it's literally just check the state of the computer get the next instruction run the instruction capture the state of the computer compare the state of the computer to the initial starting point does it seem to have matched what's required for this task if yes move on to the next thing if not go back and start again that's sort of a paraphrased way to think of the the state machine So this tells me I need to stop thinking about being able to give my large language model a big gnarly problem or amazingly amorphous goal like go find me something that I can report to Apple for a bug bounty.

and break it down not into a whole lot of series of complicated, interconnected, interwoven steps, but actually, I think the exercise here is to think about frame what you want the agent to do, then think about how would you and or the agent be able to break that down into a set of almost like homogenous work units that can fit within a very simple state machine, a very simple loop.

That's how essentially this benchmark achieves its long horizon or its long running persistence.

Because if you imagine a flowchart or a very sort of complicated Gantt chart or a diagram of all these steps or a graph basically is what I'm really trying to say.

If you imagine a graph, there's lots of forks, there's lots of edges and vertices, and at each one of those, if there's a degree of novelty or difference to them, then that's where something could fail.

And if it's only going to fail there, you might not notice it until you get to that step with that particular construction.

They want to see project management professional designation, commonly known as PMP.

They want someone familiar with Gantt charts, critical path analysis, resource allocation, risk registers, project management software.

And yes, those are all useful skills.

But in my experience, it's not what separates an exceptional project manager from an ordinary one.

If we don't learn how to use it, I think we'll be left behind.

You can make AI plan for you now and create a Gantt chart for you now so you can stay on track with your projects.

And I think it is amazing.

So I talked about, I think in a past episode, about planning backwards.

I didn't clarify to all of you.

So it's just the practical things of living with AI.

So when I say, have a moment to set your week, I'll sit at the beginning of each week and just plan everything based off the Gantt chart of my life and go from there.

And I think this episode, now that I'm saying it more, will probably be for the five to 20% of you that are like me, that have been silently trying to figure this out for years.

So I think good for you, basically.

But your Gantt charts look great.

um we're recording shall i shall i lead us in fire away excellent excellent excellent um okay well hello everybody and welcome to uh hv uh i am one of your co-ghosts john joined as always by my friend my the the demon on my shoulder uh roslyn ros how you doing

And on what the shoulders of giants, et cetera, and so forth, I stand.

The construction schedule, same thing.

I fed it all my Gantt charts because I continually update it.

I'm sure you do, too, as you

finish.

Yeah, I don't know.

That Gantt chart is just blowing my mind that you're just like, first we have to finish the airport.

Then we can finish the track.

Then we need to get a grader out and start grading out a track.