Cory McCartan

If you've noticed a distinct dialect emerging in frontier AI models and struggled to understand what they're talking about, you're not crazy! We turned to psycholinguistics to investigate what makes the writing style so weird, and why this might be happening 🚨New preprint! 🧵

So I think that this is an is/ought thing, and the ought is even a little underspecified. Like from a Rawlsian standpoint, we should orient the society in a way that maximizes a certain kind of civic engagement—which includes, at minimum, some sort of basic level of informedness. BUT

If the Refine people genuinely think their tool improves science, they should open source it.

Getting more state-level institutional power via the midterm elections is another significant way to prepare to counter a 2028 coup attempt (h/t for the addition, @sethdmichaels.bsky.social). Cuts off state-level manipulation schemes pre-vote and count or electoral vote falsification schemes after.

Yeah, extremely revealing. Healy says basically if they describe what Trump does as a 'lie' too often, they will lose access to sources.

Wrote up my thoughts & advice on computational research workflows! Have been chipping away at this for a while and finally finished writing something about each of the areas I wanted to touch on. Posting in case it is useful! corymccartan.com/workflow/

A great paper and enjoyable read by one of my PhD advisors, but very important to remember that rho_R,G here depends on n/N! So it is not as straightforward as bias growing with N

like all things considered, if there are two camps of people who are basically wrong and loud about it, i'm more bothered by the camp with structural power and adjacency to fascism. i just want the pushback to be strong enough to resist a light breeze

Attaching some random screenshots but could’ve done this across hundreds of city blocks or stretches of road.

"This election is about the threat of trans kids" is the worst possible messaging for Dems yet so many candidates are leaning into it. No voter will flip R->D over it. Low-info voters read this as "you're focused on bullshit that doesn't affect me" while the base reads this as "you're an asshole."

The 2025 American Community Survey should have come out today. But it has been delayed because of unusual political encroachment at Census. ACS drives business and policy decisions, especially in local communities, and is the primary input to Census’s immigration estimates.

Have been incredibly busy these past two months, but finally really turning my attention back to my upcoming appropriations paper. Some of the data are not 100% done yet, but I want to focus on how much domestic discretionary funding has been cut in the last few years. Posted only on Bluesky.

Half of our seminars should be pre analysis plans and the other half results. Imagine if people had an up front stake in your research, and imagine getting great input before you finalize your analysis strategy. It should be the norm.

NYT poll of LV shows D+9 generic ballot ±3.2. Plugging that into my simple congressional swing model (tinyurl.com/cmchousemodel) gives 241D–194R, with 94% chance of D win. Effect of redistricting in that environment is R+4 seats, with TX and FL doing the heavy lifting, and NC slightly backfiring

Others have said this but it’s truly insane that Brett Kavanaugh, lover of the major questions doctrine, thinks there’s a good chance USPS can use a vague grant of authority over mail processing to radically alter absentee voting procedures in all 50 states without congressional approval. Come on.

From Alito dissent on mail ballots (L). How can this possibly be squared with the "major questions doctrine"!?!? (R from WV v. EPA)

the other strange thing about this is that the 2024 election result was exceptionally narrow and yet commentators left and right talk about it like it was 1984

This is cool but I think an over-use of RD - CEF really looks like it curves at the cut point. But why do we expect a jump? Impact is probably higher for internal locations - so the relevant treatment intensity isn’t at 0.

He literally goes around with this slide. The same 'proof' would imply that no stationary AR(1) process with unbounded increments can exist. Error probability is not constant!

you could basically predict the direction public opinion under trump if you took the view that a) the 2024 election was about inflation and b) "wokeness" wasn't especially salient nor was it especially unpopular.

Ofc I say this and personally put WAY too much effort into reviews. And then I die inside when my papers spend six months under review or get torpedoed because someone was not on board with my type of paper existing or are evaluated by someone who doesn't know how math works. So there's that...

It’s a new @adambonica.bsky.social joint! data4democracy.substack.com/p/the-bulwar...

America’s unions are proud to endorse @sbworkersunited.org’s boycott of stand-alone corporate Starbucks stores. Workers are fed up with unchecked corporate greed, and we’re standing with them in their fight for a fair contract. No contract? NO COFFEE! ✊ https://www.boycottstarbucks.net/

What's most upsetting me as a journal editor is that many papers we receive where AI use is disclosed for editing and language refinement actually appear to have been ruined rather than improved by AI. We get what seem like promising underpinning studies, but totally obscured by over-complex text.

Very concerning the NYT killed this excellent piece at the behest of the scammy firms it exposes

Really excited to see that my paper with Erin Hartman on assessing non-ignorable nonresponse in survey weighting is (finally) out! doi.org/10.1093/poq/...

Happy birthday to the Voting Rights Act. Complicated feelings on this particular anniversary.

Mechanically, what this means is that it’s assuming fairly smooth interactions between covariates. So if you want flexible models of interaction you have to build them in yourself. Which is, after all, what you’d expect with BART.

This is definitely interesting. It’s probably worth noting in high dimensions that mixed sobolev spaces are much smoother than usual sobolev spaces. So think of this kernel as closer to a squared exponential than a Matern-1. But still rough enough that the paths aren’t analytic.

Random tree features are also implemented in my 'bases' software! corymccartan.com/bases/refere...

Fascinating and clear paper by @corymccartan.com and @melodyyhuang.bsky.social, greatly enhancing our understanding of how Bayesian Additive Regression Trees (BART) works and why it is so effective. A must-read for my fellow BART enthusiasts. #statssky #causalinference