Azeem Azhar

I'm just going to say this.

I realize I knew nothing about conducting except for watching that film, which had, I think, Cate Blanchett in it.

But, you know, when you're conducting an orchestra, you sort of need to know the capabilities of the people who you are conducting.

And one of the things I've noticed as I've started to move from sort of single agent coding to multi-agent systems and working parallel with 6, 8, 10 of these things at a time,

is that you do need to understand those systems.

And I've even discovered, and this is kind of curious, that the agents are starting to understand their own limitations.

I was building something that's a kind of internal research tool a few days ago that involves a lot of different agents.

And at one point, Claude said to me explicitly,

Don't use me for this.

Go and use chat GPT because it's tougher and more cynical than I am, which I thought was a really interesting bit of self-reflection.

It's quite a strange moment.

And that is evidence, I think, that we're not going to have that singleton AI, all-powerful AI.

It is that society of AI that I wrote about a couple of years ago.

Or if you saw the recent essay about the world of spiky minds, that's also sort of reflective of that.

Lots of different models, lots of different capabilities and tones, and the need for us to be able to orchestrate and understand across them if we are actually to be more than individual contributors.

So there's a reality shock here at check here, which is the usage gap.

So at the end of 2025, you know, ChatGPT, alongside everyone else, by the way, launched their sort of year in 2025.

Everyone's aping, aping Spotify.

They released their year in 2025.

If you got one of those, why don't you share some of your highlights from that year in 2025 in the chat?