ChatGPT - This is interesting

[George Ford]

I'm not sure how complex a code it could produce, but here's a test of some simple tasks.

[George Ford]

bootstrap

[Jared Greathouse]

I need it to write code for augmented synthetic controls!

[George Ford]

I don't think would do.

[Jared Greathouse]

Oh i agree! You'd need to break it down into the subroutines and the optimization method AugSYNTH uses, it would NEVER work in the super simple way I suggested. But it does look very cool!

[George Ford]

Have you tried allsynth?

https://www.stata.com/meeting/us21/slides/US21_Wiltshire.pdf

[George Ford]

Boo

[George Ford]

Might look at this.

https://twitter.com/aspaglayan/status/1378124828524179456?lang=en

[Jared Greathouse]

Yep that's my friend's command. When i asked him, he said augsynth is pretty much completely Ridge regression instead of OLS followed by ridge. Justin also noted how R and Stata optimize sort of differently, so he said they might not be totally comparable. But I'll see! Maybe I'll test them side by side.

But yeah, chatgpt seems super useful, and it could be sharpened over time for programming

[George Ford]

It seems like it could answer a bunch of the more simple coding questions that get asked here.

[George Ford]

For those who don't want to write it up themselves.

[Jared Greathouse]

I wonder how nice it would play with data collection. Like, even if I asked "Where might I get Spanish state GDP/cap from 1990-2010", or even if I asked it to scrape together python code to do that (if I fed it like a link or something).

Either way, I don't take think it'll overtake ado programmers any time soon

[George Ford]

This could be useful.

[George Ford]

As for the Spanish GDP. I don't use Python so don't know if it works.

[Jared Greathouse]

It got the code for the nation (state), not each of the 16 Spanish states, but hey, either way, this would work nicely if the dataset could be found.

It would also be super useful to scrape together Wikipedia tables if they had useful data