Bret Beheim

This is a great idea. I'd rather the norm in science to be wrong for the right reasons, than right for the wrong ones.

I picked this up from a 7-11 in 2003 and think about it often

Come work with us! And get in touch with any questions you might have about the position, our labs or living/working in Germany #PostdocWanted

It's hard to communicate to non-USAians how deeply sad and upsetting today's actions by our government are. They were wrong in 2003 in Iraq, and they are wrong today. History will judge us all for this barbarity

Last day of February in Germany be like

a gpt in a sublime 200 lines of pure Python — it is all there. Incredible for teaching students (and yourself)

karpathy.github.io/2026/02/12/m...

There's always "Clan of the Cave Bear" if you want Neaderthal-human couplings, though that's even worse than ACOTAR

I'm learning about hypergraphs now and am curious about this - is the joke that you can accomodate interaction effects in a DAG?

Just discovered an insane new form of co-intelligence where you briefly share the mind of a great thinker in history and then a portion of their mind travels in yours for the rest of your life. Calling it a "book."

the podcast radicalization gateway is real

Also RIP my German homies who still Luft every day (open up all their windows to let the relatively clean, warm air out to replace with filthy cold air)

One of the few downsides about living in Leipzig (and eastern Europe more generally) is the absolutely atrocious air quality. Definitely regretting biking into work today....

I just read the declaration that Kira Kelley asked J. Blackwell to consider.
This immigrant describes being
-unlawfully arrested
-taken from one overcrowded & filthy prison to another over 19 days
-held incommunicado
& ICE never telling him a court ordered his release

He describes an American gulag

as I'm revising my course materials, I keep stumbling upon cool @mc-stan.org developments.

Current favorites:
1. your model has funnels and you exhausted reparametrization ideas: metric = "dense_e" makes your HMC learn about covariance btw parameters. Sloooow, but effective!
1/

My dog's post-surgery face is a pretty good signifier of the state of my household right now

Does literature evolve one funeral at a time? Abstract. The cultural evolution of literary fiction is rarely studied, but rich literary data can help address some of the general problems of cultural ch

I think Oleg and my paper from last year is a pretty nice combination of theory and big data for trendlines in a longitudinal corpus. It's not easy to identify exact mechanisms in observational, historical data, but we might be able to rule things out in a force-based approach

Today at the Leipzig Hauptbahnhof - a novel solution to the trolley problem

It's one of the benefits of having teenagers - Hopplo charms are actually some of my daughter's best sellers in her crafting biz

My personal fav is Scorbunny -> Hopplo

Schlurp YouTube video by Spencer H

My daughter tells me her favorite German pokemon is Lickitongue -> Schlurp

Very happy to see our ice-fishing paper on the cover of @science.org this week! 🎣🎉

We tracked large groups of Finnish competitive ice-fishers to study how social foragers use social information when searching for resources. 🐟

Link: www.science.org/doi/10.1126/... (contact me for open access)

timeline is terrible, time for cozy office vibes

Studying social transmission using STbayes Post provided by Michael Chimento. When studying animal culture, it’s important to establish whether novel behaviours or information have spread through social contact, or are rather innovated or p…

New blog post!!🚨

Michael Chimento gives an overview of the new R package STbayes, designed for creating, fitting and understanding Bayesian models of social transmission 🌍 🧪

Read the blog here 👇

Why Risk it, When You Can {rix} it: A Tutorial for Computational Reproducibility Focused on Simulation Studies

May be of interest to the reproducibility folks: New tutorial on computational reproducibility for simulation studies just dropped! felipelfv.github.io/Why-risk-it-...

by @felipefv.bsky.social, Jason Geller & @brodriguesco.bsky.social

It's impressive to see how far things have come: github.com/rmcelreath/s...

Before it became REthinking, the course also had a pretty different take on Bayesian stats!

There was no book yet, but we read from @bbolker.bsky.social "Ecological Models and Data in R" and of course Gelman and Hill

Some trivia to keep me off the newsfeeds - I remember when @rmcelreath.bsky.social's stats course was just called "Statistical Thinking"