Michael J Curry

if i tell it "be very careful to make sure the code compiles", seems to be able to get it first try on some other simple tasks. of course no general conclusion on that prompting strategy. it's extremely funny that this is how computers work now

i just asked o4-mini-high to code up a self contained Fortran version of running PCA on some random vectors, and it didn't compile first try (did second try after being shown the errors). haven't checked correctness but wouldn't be shocked by subtle error somewhere.

Frank Yang, Kai Hao Yang
Multidimensional Monotonicity and Economic Applications
https://arxiv.org/abs/2502.18876

imagining a game where people commit to have a proxy play a mixed strategy for them doesn't seem like such a stretch. and once you're in that world, committing to let a proxy play a correlated strategy for everyone seems pretty natural too. i guess that's still pretty mechanism-design-ish though

🚨New book announcement🚨 Kevin Hartnett’s THE PROOF IN THE CODE (coming 2026) tells the gripping story of the birth and rise of Lean, a Microsoft computer program transforming the world of mathematics. A timely challenge to our assumptions about who–or what–can do math—visit quantabooks.org for more.

i believe this dialogue is the quota for the irritating AI grammar checker, not compiler. if also failing maybe ui bug or something

tried to get gemini deep research to do this and the result was Bart Simpson level

“…Mustard, a key ingredient in the mustard-emulsion method, boasts an ancient history. Its use dates back to ancient Egypt, where it was primarily used for medicinal purposes…”

In the interest of generating more ML/AI discussion here - here's a really interesting looking paper from Mason Kamb and @suryaganguli.bsky.social on an *analytic* theory of diffusion models. t.co/SYkAAh6k4C

even relaxing a lot of assumptions it seems hard to escape maximizing over discrete sets somewhere. i guess some behavioral models like rational inattention also have the pleasant side effect of smoothing the problem, but i don’t know if people find them credible or not

learned the hard way by taking derivative of an optimization problem and watching gradient descent not converge

one partial explanation is in physics it’s usually safe to assume everything is nice and smooth. in economics, you have agents that make optimal choices, which tends to create discontinuities, often at exactly the point you care about. so there has to be at least a little more analytic rigor.

P-CTC also =PSPACE. in other words a quantum computer would not be useful if you already had a time machine

“Here is a Philip Larkin poem about cryptocurrency.” The Invention Money is a thing you earn by the sweat of your brow And that’s how it should be. Or you can steal it, and go to jail; Or inherit it, and be set for life; Or win it on the pools, which is luck; Or marry it, which is what I did. And that is how it should be, too. But now this idea’s come up Of inventing money, just like that. I ask you, is nothing sacred?

early non-chatbot GPT3 was mostly bad but got a hit occasionally. chat versions seem to never

hello!