OpenAI Codex

You did.

But my number one is, you know, the mirror universe side of yours in a way, right? Mine is Codex, right? Okay.

Which is OpenAI's desktop product.

Codex, ChatGPT, ChatGPT Work.

It's kind of all kind of like, you know, started to kind of coalesce into kind of one platform.

Okay.

Codex is my daily driver.

It's where synthesis happens, documents are created, workflows are happening.

So let's talk about where I get my work done first.

So, you know, we've had these episodes where I've been a big Codex fan, and I've been using Codex for a while, actually.

The problem with the Codex app that I've had is, first of all, it got slow and bloated.

Like, it would slow down quite a bit, etc.

And the other thing that got slow is the models themselves.

As a matter of fact, I measured the speed this morning just to check.

And I measure it regularly.

I have this thread on Codex.

let's say they generate...

But I'm saying this again, you know, I'm saying Codex is a great tool.

But let's say they

generate $30 billion.

And see, it looks like a lot of these bots work with a lot of other things.

Like here's an import bot that brings your setup from Cloud, Core, Codex, ChatGPT.

So it looks like it works with a lot of other softwares out there.

Boy, I could sit here and read through all these.

So this time, I'm surprised you've not guessed.

This one is a month's subscription to Codex Pro.

Okay.

which is ChatGBT's Codex Pro model.

For clarification, because when I looked into it, there are subtle varieties.

It is the standard 20X, it's called.

I don't even think there's a use case for Hermes because you can do everything in MCP, right? Is there a use case for Hermes?

I mean, so we integrate the same way to all of those Hermes or Cloud, Codex, all of them access it in the same way and automate it.

The open Cloud Hermes had this extra feature of, you know, ability to kind of, you know, cook up the tools for you.

And, and, and, definitely it's not like impossible today to just build something like creep.

hop on a phone with somebody now and they booked us for a call.

And they're like, so what are you using, Claude? And I'm like, we could be using Claude, we could be using Gemini, we could be using Codex.

I mean, it could be a million different tools.

But people behind the scenes, I will say, we're constantly testing things.

As smart as today's AI systems are, do you ever wish that they would just watch you do all your work and then magically do it all for you? Well, that's what we have now with a new feature from OpenAI and Codex called Record and Replay.

Because here's the reality.

As we are continuing to shift from the responsive chatbot era to the proactive agent era.

There's still a lot of manual work that we have to do, whether that's scheduling and automating your workflows, creating new skill files by hand or whatever it may be.

Whether you're using ChatGPT, Codex, Claude, Copilot, or Gemini, there's a lot of manual work that needs to go in to create these repeatable and autonomous processes.

But I think that may start to change.

And I think that with what this new feature is in Codex Record and Replay, we have maybe a preview of what's coming next as we have these extremely powerful super apps that live on our desktop and can do work for us.

So that's what we're gonna be going over on today's show.

So there's a new sort of, you know, new features are always rolling out for AI.

And one of the new ones is Codex, which will build things for, it's really good at making websites or, you know, making dashboards and like coding up stuff.

And so now you can plug-in things like email, calendar.

There's tons of plug-ins to add.