Really? You don't think any of the other tools are useful? Or just not "a lot"

True, but I know folks who use Claude Code w/o any MCPs and they're leaving a lot on the table.

Love this. Kid is going places

faculty.wcas.northwestern.edu/gep575/Bayes... I think you can only get something close to the LM tests, AR isn't possible

I would just hedge my bets everywhere and invoke Bernstein-von mises

🤣

We first note that hand-wringing about the decline in US college enrollments has mistakenly linked such declines to the price of four-year colleges.

But the decline is entirely driven by two-year community colleges (and by for-profit colleges). The four-year sector is the dog that didn't bark.

Yeah, I guess then it's relative -- now the more scarce thing would be a handmade x or y since time is one of the more scarce inputs.

Or, for example, learning how to build something to make a gift for someone.

Or, learning a language/trick to amaze someone

I think the usual econ argument about this relates to the modern trade view -- abundance through the multitude of trade allows for more kinds of magic to manifest.

idk not to mention how very nuanced and normal the actual response here was

And I read (and did!) plenty of Bayesian estimation stuff from Imbens, so I think more of the guilt lies with the practitioners than the econometricians