Whoa. "[F]inetuning exclusively on Haruki Murakami's novels unlocks verbatim recall of copyrighted books from over 30 unrelated authors...Our findings offer compelling evidence that model weights store copies of copyrighted works." papers.ssrn.com/sol3/papers....

29 years of #rstats community knowledge was sitting in hard-to-search pipermail archives. So I built a more modern home for it. Introducing the R Mailing List Archives: 631,000+ messages from 32 lists, fully searchable and available as open data. r-mailing-lists.thecoatlessprofessor.com

Statistical Rethinking 2026 is done: 20 new lectures emphasizing logical and critical statistical workflow, from basics of probability theory to causal inference to reliable computation to sensitivity. It's all free, made just for you. Lecture list and links: github.com/rmcelreath/s...

The Atmosphere is a new open network. The features: - Your account works on all atmosphere apps - You can switch to a new provider with no fuss - Easy to make your own apps on it - Works great with personal websites And, Bluesky is an atmosphere app.

Anyone else spoiled by R's pkgdown and find python's mkdocs or sphinx a bit tedious and config-heavy. Check out @richmeister.bsky.social 's awesome new {great-docs} as a batteries-included alternative to spin up an effective docs site in <15 min! 1/n 🧵 github.com/posit-dev/gr...

Today is the last day to apply for an Opportunity Scholarship for posit::conf(2026)! Our Opportunity Scholarship provides travel, lodging, & registration to attend posit::conf for underrepresented groups in data science. Learn more & apply by midnight tonight: posit.co/blog/apply-t...

I wrote about why @knightfoundation.org invested in @bsky.app: philanthropy can act when mission & opportunity align. We believe in @jay.bsky.team's vision for a better social web—& in ideas (like @masnick.com's) that grow out of the research ecosystem Knight has long supported. kf.org/kfbluesky

Have encountered one of the cleanest, most beautiful Simpson's paradoxes to date in my professional career but because it's work-related I can't post about it So I guess I'm just... bragging(?) because its textbook-level perfect

I'm rerunning a 6 year old ETL script that is *so* bad, but I'm always too lazy to rewrite. (Only need it sporadically in even-numbered years, IYKYK) Makes me so grateful I "grew up" before tools could help me avoid bad designs. Learned so much and found so much joy fixing the kludgy stuff

Six months from today, YOU could be joining us at posit::conf! A topic I plan to explore is how we best borrow ideas from across different fields (from DS to DE, team-of-one to enterprise, etc.) Ironically, that's also one of the magical things about the conf 1/2

A fair coin "knows" π. Stop flipping when heads first outnumber tails. The expected fraction of heads is π/4. Average many trials → estimate π. Result by J. Propp, animated for #PiDay. Made with #Python #NumPy #Matplotlib and @marimo.io #Mathematics #MathArt #CreativeCoding

Nothing makes me feel older than working on a random silly side project that absolutely would have crushed it on 2018 data twitter and yet is now so wildly out of step with the moment

The other week I was roasting how finance folks say “up and to the right”, but I guess j actually like that better than “up, pretty much asymptotically so”

The only feature of 1Password that matters is their business dies overnight if they get hacked so they’ve thought harder about security than anyone you know. You can’t vibe code that in two evenings no matter how much you ask Claude to “make it secure”

“They were careless people, Tom and Daisy—they smashed up things and creatures and then retreated back into their money or their vast carelessness, or whatever it was that kept them together, and let other people clean up the mess they had made.” - The Great Gatsby Exact meter, exact message

We are covering 40 people's travel, lodging, and registration for posit::conf() this fall! If you are from a group that is underrepresented in data science or open source, please consider applying for the Opportunity Scholarship—we'd love to have you join. posit.co/blog/apply-t...

Funny to see progressive disclosure as an "agentic design pattern" when, friends, that's literally just good comms. I swear by Bottom Line Up First for any professional information sharing Bonus link to my fav Quarto hack for doing this in analytics-heavy work www.emilyriederer.com/post/quarto-...

Did WaPo's mass layoffs include all their pricing folks or what? Pay monthly netting ~$26/yr or upfront at $40/yr 🤔

This from @petridishes.bsky.social is brilliant, and should be made into a documentary. www.theatlantic.com/magazine/202...

"Anonymous accounts massively profited from absurdly well-timed bets on geopolitical events" is absolutely guaranteed and recurrent of a news story as news anchors reporting about Thanksgiving travel delays

Independent news media needs a "financially support us but we promise to not tempt or enable you with access to any premium ungated content" tier for those of us that appreciate the mission but are absolutely maxed out on content

There's a moment in every data engineer's career when they discover they can query a 10GB Parquet file on their laptop in seconds. That's the DuckDB moment. It changes how you think about what requires a cluster and what doesn't. Spoiler: most things don't. ssp.sh/blog/enterp...

This was a fantastic, honest episode! Hard to imagine a group that clearly cares more about the craft of ergonomic tools than Astral, so really interesting perspective on what agentic coding both gives but takes away

I think few things have impacted my technical comms skills (such as they are) more than before-times Twitter. Amazing to discover how much you can communicate in as few characters as possible! Felt like a game then but really a useful life skill

Tired: Logistic regression Wired: Pregenerative AI

Just saw Leah W. share this on LinkedIn - great round-up of AI contribution policies! By @melissawm.bsky.social github.com/melissawm/op...

Rereading this excellent post by @vickiboykis.com, "I want to see the claw", in a world where "OpenClaw" exists 😭 vickiboykis.com/2025/10/20/i-want-to-see-the-claw/

This should be a much bigger story. Kegseth is essentially saying he wants to use the Anthropic software to commit war crimes and will therefore not agree to be bound to well established US and international law rules. Outrageous.

The thing people don't get is that when Sec 230 is repealed, platforms could become much more restrictive in their moderation to avoid legal risk. Smaller platforms like BSky might struggle to survive due to higher compliance/legal costs and some lawful content might be removed preemptively.

My nephews got Learning Resources Christmas presents this year — thoughtful quality toys and a great reminder to stand up for what you believe in (granted they are still working on standing generally) Check them out!

You can also show your medical data to your dogs for a second opinion. The benefit of that is that your dogs aren't harvesting your private data.

Bluesky is the new science Twitter, new study by @whysharksmatter.bsky.social and Julia Wester concludes! "Results show that for every reported professional benefit that scientists once gained from Twitter, scientists can now gain that benefit more effectively on Bluesky than on Twitter."

Plenty that others will say about all the semi-dystopic Super Bowl ads, but Monday morning the one in my head is every employee was vibe coding their own apps Sprawling ungoverned internal tool dev has notably worked out so well in corporate BI tools 😣

Reminder when you watch the Intuit Super Bowl ads, they have Super Bowl ad money because they are a successful rent seekers who have worked for decades to kill free, quality, public tax preparation services donmoynihan.substack.com/p/the-death-...

Got #data ideas to share? Two awesome confs have CFPs ongoing through February! @posit.co ::conf submissions open thru Fri 2/20 posit.co/blog/posit-c... Applied ML Conf (feat @vickiboykis.com !) submissions open thru Su 2/22 appliedml.us/2026/

The weirdest thing about reading financial journalist is their love of the phrase “up and to the right”. I’m no time series expert but I guess I wasn’t worried about the “to the right” bit. Thought that was kind of non-negotiable

Had a great time on @posit.co 's Test Set pod w/ @mchow.com @hadley.nz @wesmckinney.com! We talk about moving between R, SQL, python and the strengths of different analytical tools for diff data tasks. You won't believe what proprietary language gets a shout-out (Stata!) posit.co/thetestset/e...

Never underestimate the quest for knowledge no matter how irrelevant it may seem in the moment If I hadn’t gone to a public university, I honestly wouldn’t have ever bothered to watch a basketball game. But now? “Boxing out” is a top ten skills for boarding public transportation

Weeks after writing about how the best ideas bleed btwn R and python, I find out from @stephenturner.us 's excellent blog that the #rstats world is attempting their own Rust-based analog to `uv` (for deps mgmt not packaging) Haven't tried but neat to watch a2-ai.github.io/rv-docs/

Last 2025 post, on @python.org & @carpentries.carpentries.org values, a great @posit.co conf session feat @mchow.com @richmeister.bsky.social @davisvaughan.bsky.social, the magic of #rstats #python dev cultures sharing best practices, and random #rstats history www.emilyriederer.com/post/py-rgo-...

I know of a 40,000 patient clinical trial where the SAS programmer determined the key secondary outcome as positive if Y=time to stroke < maximum follow-up time. Y=missing -> positive outcome because with SAS missing < anything. The error still stands.

I feel like #lazyweb isn't what it used to be, but anyone in #econsky happen to know of a good package for implementing fuzzy regression discontinuity designs in python?

Does anyone want a survivorship bias shortbread

Wondering what we lose as tech writers write for AI training vs humans. The lovely `polars` docs often use nice reprexs to demonstrate syntax but then note if the technique shouldn't be used in such a trivial case. Would someone write this now or worry AI picks example w/out context?

Great taxonomy for managers, as well! So important to be clear when feedback is a must-have, nice-to-have, or curiosity question you don’t reasonably expect to get answered

Continuing my #python Rgonomics posts for the #rstats crowd, wrote a short post about the different ways to use (non-polars) user-defined functions in a pipe Not the most groundbreaking thing, but one of those "the thing I needed to read a bit ago" posts (1/) www.emilyriederer.com/post/py-rgo-...

Every year around this time I’m surprised/disappointed to find there aren’t good places online to print custom 365 day calendars Do you people like.. not maintain lists of 400+ pithy thoughts on the same topic? (Seriously, does anyone know where this can be done?)

1. This is reprehensible and should not exist. What are we doing? 2. Mildly amusing picturing AI me, learned from my digitaltraces; family and friends reaching out in their moment of need, and I'm just spouting off about data quality checks and column naming conventions

Favorite talks from day 1 of @causalscience.org 's #CDSM2025 🧵

Truly one of the best data science events that I look forward to all year long! No sales, no hype, just exquisite thoughtful yet practical methods. Taking two days off work to attend. Don't miss out!