Dan Shipper

all the things that the model comes back with, you're like, I don't know if this is like, totally right, or like, it should have done a little bit more research here.

It's just really good at getting the models to do the maximum possible amount of work.

So for important stuff, or stuff that requires a lot of thinking, it's a really good workflow to use.

That's really interesting.

Wait.

So what are you, when you write with it, what's your workflow?

And you like that better than using 5.4 in ChatGPT?

That's interesting.

I think this is a really interesting thing.

I mean, I use Codex much more than I use ChatGPT for things that I used to use ChatGPT for.

And the thing that happened is around the time when me and Kieran were having this whole realization about 3.7 and do you need to touch the code and whatever, a little bit after that was when GPT-5 came out.

And GPT-5 was a very interesting model release because they continued, even though all of this agent decoding stuff was happening, they continued to push forward this split between regular knowledge work and vibe coding happens in ChatGPT and professional pair programming happens in Codex.

And

They stuck with that split from GPT-5 really until like the last two or three months.

Yeah, exactly.

And I think that really hampered them because what Anthropocene was able to do is –

Cloud Code A, people started to be like, there's a whole new engineering paradigm that I can't do with Codex because it's too hobbled.

It doesn't let me do this.

And then people were like, but I could also do it for all this other work.

And so it started to explode.