Tyler

But the magical part of computer use, and the team really cooked here, is that it can use applications in the background.

So you could be doing something in one app and the agent could be doing something in another app.

And that's important because it means you can actually delegate, which means you can give the agent hard tasks that take us some time to do.

So, yeah, I mean, the reception around that was actually awesome.

I thought we got people noticed sort of just how hard and magical that is more so than I even expected.

So, yeah, we've been really happy with that.

So there's three things going on there.

First of all, GPT-5.5 is our best model ever for general work or knowledge work.

And so it's really good at using computers.

The next thing is, well, what harness do you give the model?

Or what information is the model seeing?

And what tools does it have to use the computer?

A lot of early versions of giving a model access to a computer were just giving it screenshots of the computer.

But there's a lot of secret sauce in our implementation where the model actually gets text representations of what's on screen from frameworks like accessibility.

And so the model is much more efficient when it has access to all this information.

And then the last bit that I honestly think, well, I don't know if I would say it's underappreciated because I feel like people really appreciate it, but it's the level of craft that was put in to how it feels when the agent is using the computer.

So for instance, you could totally just have the agent click around on your screen

and just have that be invisible.

The computer is updating as clicks happen, but the team put a ton of care into exactly the animation that this mouse cursor takes as it goes between the different click positions.

Yeah, it was really fun to talk about that and jam on that with them.