Yannis Antonoglou

there's almost like a discovery that we need to do.

Once you have these powerful agents, what does coding look like in this new world?

We need to kind of like almost like rethink how we just like code and what coding looks like.

And then you can just like think of different ways and different paths of doing that.

And there are like, yeah, many kind of like different companies trying to just like almost do slightly different things.

At the same time, you know, most converge to coding agents as like the solution, like in some way, in some form.

So, I don't know, I think it's too early to just like say exactly what coding will look like in even like three years from now.

Yeah, I mean, for us, again, it's all about having agents that you can really trust, that when you ask them to do something, they'll just go and do it, and they'll just self-correct.

Even now, you just have these agents, they will try to do something, they will just trip over, they will just go into circles.

They might kind of waste tokens on dead ends.

They're just not as efficient.

So having stronger agents is definitely the thing that's needed for any future.

But we know exactly what we need to do there.

We just need to make these agents more reliable and better.

Now, what I'm trying to say is that there's another question.

Imagine that you had access to extremely powerful agents.

What is the best way for you to interact with them?

What's the best UI for you to just coordinate them and to delegate tasks to them and just keep track of what they've done and what they haven't done?

What is the best way to run your team of agents?

And I think I've seen different ways of approaching the problem, but