I just whipped up this little #QuartoPub site last week that demonstrates how I teach p-values/hyp-testing through simulation both with live OJS and with #rstats, and I think it's super neat! It has examples for diff-in-means, diff-in-props, and regression slopes nullworlds.andrewheiss.com #statsky

I built an R package that turns Shiny apps into UIs that render directly inside Claude Desktop or ChatGPT. It's called shinymcp. Drop-downs, plots, tables all inline in the chat. github.com/jameshwade/shinymcp

You can totally point out that some aspects of AI are overhyped, you can believe that AGI is not possible, you can criticize how the companies and governments developing AI are using or being coopted by these tools. There is a lot to criticize. But "it doesn't work and is fake" is just wrong now.

Join us on Tuesday at the Data Science Lab 🧪 We are joined by @sara-altman.bsky.social, who will show us how to explore and analyze data using AI assistants in #RStats or #Python! Feb 3 @ 12 pm ET: pos.it/dslab

NSF GRFP applicants (and mentors): Was your application Returned Without Review and deemed ineligible despite fitting in the allowed topics? 1) Write NSF 2) Write your Congressperson 3) CC us at [email protected] so we can compile + follow up Details and template at grant-witness.us/grfp-letter

Nice post from @simonpcouch.com here, on why the "median" LLM query is not a good way to examine the system's broader energy costs. Visualised very nicely: www.simonpcouch.com/blog/2026-01...

In this week's newsletter, @simonpcouch.com and I share some interesting tidbits from Claude's constitution, an estimate of the electricity use of coding agents, and an update on our plot interpretation work.

"LLMs [only] do a great job at interpreting plots that _don't_ contradict their expectations—it's sort of antithetical to the spirit of science." - @mike-thomas.bsky.social. Thanks for the coverage, yall! More on @sara-altman.bsky.social and I's bluffbench eval: posit.co/blog/llm-plo...

ollama recently implemented support for Anthropic’s Messages API, meaning that you can hook up Claude Code to an LLM running on your laptop. This is really neat, but I’ve seen some posts about how you can now have “Claude Code for $0.” A word of caution: www.simonpcouch.com/blog/2025-12...

Heck of a weekend. Timeline cleanse from the local sledding hill:

Imagine what’s happening in the camps.

Here's a quick little example showing off tidy() vs. model_parameters(): andrewheiss.quarto.pub/parameters-v... Maybe someday I'll make a longer, more official blog post showing glance() vs. model_performance() and augment() vs. marginaleffects::predictions() 🤷‍♂️ #rstats #easystats

This is the stuff I wish I hope to see more of. In a sea of similar posts about #vibecoding, it's refreshing to read @sara-altman.bsky.social & @simonpcouch.com digging into the whethers /whys of AI's utility in data analysis. We need lighthouses in this #AI storm 🌊 #databs posit.co/blog/llm-plo...

More on LLMs and plot interpretation: they do fine in normal conditions, but struggle when the plot conflicts strongly with their priors. @simonpcouch.com and I investigated why and what might help: posit.co/blog/llm-plo...

ICE kidnapped a 5-year-old and sent him alone to a facility in Texas. Hell isn't hot enough.

Whenever I read discourse on AI energy/water use that focuses on the "median query," I can't help but feel misled. Coding agents like Claude Code send hundreds of longer-than-median queries every session, and I run dozens of sessions a day. On my blog: www.simonpcouch.com/blog/2026-01...

In this edition of the @posit.co AI Newsletter, a sneak peek at a new agent coming to RStudio and reflections on Claude Code with Opus 4.5.👀 posit.co/blog/2026-01...

I sent 200 pull requests using Claude Code and wrote about the experience. It's pretty wild! For dplyr releases, we send a PR any time we break an #rstats package. This release advances a lot of deprecated functions, triggering issues in many old packages! blog.davisvaughan.com/posts/2026-0...

How do you use AI assistants in data science without compromising sensitive data? As tools like Positron Assistant and Databot gain the ability to execute code and access files, this question becomes more urgent. @simonpcouch.com and @sara-altman.bsky.social break it down: posit.co/blog/trust-l...

Soooo if you use #RStats and Claude Code: R console: install.packages("btw") Terminal: claude mcp add -s "user" r-btw -- Rscript -e "btw::btw_mcp_server()" And now Claude Code can answer questions about ANY R package installed on your system.

Turn Claude into an expert on writing {testthat} #Rstats 📦 version 3 R tests with the Claude Testing R Packages skill by @posit.co github.com/posit-dev/sk... That repo has other skills including how to use brand.yml with Quarto and Shiny github.com/posit-dev/sk... #GenAI

This whole thing is amazing, but tucked away in a dropdown at the end of the markdown is... quite seriously the best essay I've read on the environmental impacts of AI?

Happy holidays! 🎄 I snuck in a {btw} release just before CRAN went on vacation for the year. {btw} is an #RStats package full of tools for LLMs, including a new tool for running R code. Here's a quick demo using `btw_app()` to create a quick festive ggplot2 from holiday movie titles. Cheers! 🧑‍🎄

Context windows out to thwart all our beautiful dreams

In this edition of the @posit.co AI Newsletter, some 🎄Year In Review🎄, notes on GPT 5.2, and an experimental AI product for RStudio users. posit.co/blog/2025-12...

infer 1.1.0, a package implementing an expressive grammar for statistical inference, is on CRAN! In a change originally motivated by @allendowney.bsky.social's posit::conf(2024) keynote, the package now supports arbitrary test statistics. Read more: github.com/tidymodels/i...

Why do I drink coffee past noon? Why do I do this thing?

Thinking about running local models with coding agents like Positron Assistant? 💻 A new evaluation by @simonpcouch.com and @sara-altman.bsky.social suggests we aren't there yet. Between hardware hurdles and performance gaps, hosted models are still the best bet for now. posit.co/blog/local-m...

While coding agents like Positron Assistant and side::kick() are technically compatible with LLMs small enough to run on your laptop, the results leave much to be desired. New on the @posit.co blog from @sara-altman.bsky.social and I: posit.co/blog/local-m...

Great and easy to understand post on using LLMs, i.e. in #positron #rstats

GPT 5.2 is now included in our R code generation eval! The -Pro version is slightly SoTA at a substantially higher price point than similar performers. Read more: skaltman-model-eval-app.share.connect.posit.cloud

New data from @sara-altman.bsky.social & @simonpcouch.com, using the vitals and ellmer packages, looks at LLM performance metrics for #RStats. 👀 Sneak peek: Claude Opus 4.5, Claude Sonnet 4.5, & OpenAI GPT-5 lead in generating correct R code. Read the full breakdown: posit.co/blog/r-llm-e...

Episode 215 of R Weekly Highlights is out! serve.podhome.fm/episodepage/... 🤖 AI Newsl @simonpcouch.com @sara-altman.bsky.social 🎙️ The Test Set @mchow.com @hadley.nz @wesmckinney.com 🤔 Haskell for DS @jonocarroll.fosstodon.org.ap.brid.gy h/t @mike-thomas.bsky.social Sam Parmar 🙏 #RStats #databs

A new release of chores is now on #rstats CRAN! There are now some LLMs tiny enough to run on a laptop that are capable of powering chores helpers. Here's a real-time demo with a model running on my Macbook. Read more: www.simonpcouch.com/blog/2025-12...

Some closing thoughts for my students this semester on LLMs and learning #rstats datavizf25.classes.andrewheiss.com/news/2025-12...

A new release of odbc, a package that allows for connecting to various databases, is on #rstats CRAN! Just a few bug fixes in this release. github.com/r-dbi/odbc/r...

This edition of the @posit.co AI Newsletter highlights a few frontier model releases, a new R coding LLM evaluation dashboard, and a post from @wesmckinney.com on LLMs' difficulty with arithmetic! posit.co/blog/2025-12...

I get the appeal of local LLMs—free, private, no big tech. That said, they're not yet ready to power coding agents like Positron Assistant or Databot. www.simonpcouch.com/blog/2025-12...

It's Spotify Wrapped season🎁 Continuing the tradition of analyzing my music listening data with #rstats tidyverse, this time with Databot: www.simonpcouch.com/blog/2025-12...

A new release of vitals, a package for LLM evaluation in #rstats, is now on CRAN!🎄 This release includes all sorts of quality-of-life improvements; image support, precise latency measurement, better error messages, and more comprehensive logging. github.com/tidyverse/vi...

I am tremendously grateful for open source, as it’s had such a huge impact on my career. That’s one of the reasons I’m so happy that Posit has committed to the @opensourcepledge.com. Read about our contributions to non Posit projects at posit.co/blog/posit-o....

Everyone is welcome to join us at our next virtual meetup for a talk on using #GenerativeAI in R with Sharon Machlis @smachlis.bsky.social — Tech Journalist and Data Professional. RSVP 🔗 www.meetup.com/rladies-pari.... #RStats #RStatsFr #Rprogramming #RLadies #GenAI @rladies.org @posit.co

📣🚨 Very much looking forward to hearing from @frankiethull.bsky.social about the intersection of coded data viz and AI assistants! 👀🚀 Join us Tuesday Dec 2nd, at 3pm Eastern to hear about {ggpal2}, a {chores} extension. #ggplot2 #ai #chores bit.ly/RxAI-join

The LLM privacy question comes up (rightly so) on every data community call I'm on. I've had sooo many questions myself. #databs #rstats #pydata Good resource: posit.co/blog/trust-l... Also, have you seen side::kick in RStudio? simonpcouch.github.io/side/

The newest edition of the @posit.co AI Newsletter is out! Some notes on TOON, several open source updates, and a callout to two recent blog posts from @sara-altman.bsky.social and I. posit.co/blog/2025-11...

Often, the first question I get when sharing about Posit's LLM tools is "Will this expose my data?" @sara-altman.bsky.social and I wrote about the trust relationships involved when using our AI tools on the @posit.co blog. posit.co/blog/trust-l...

Introducing bluffbench, a new tool to evaluate how well LLMs actually see data plots. When we trick LLMs with secret #RStats transformations, they can miss the visual contradiction. bluffbench helps us measure this "blind spot" in AI coding agents. Learn more: posit.co/blog/introdu...

Gemini 3 is out! I've been poking at it with `side::kick()` and am impressed so far. In case you want to connect to it with the #rstats ellmer package, I wrote some quick notes in a Gist: gist.github.com/simonpcouch/...

A core capability for data science agents is making plots and learning from them. While developing Databot and Positron Assistant, though, we've seen that LLMs tend to ignore plotted trends when they're counterintuitive. From @sara-altman.bsky.social and I: posit.co/blog/introdu...

ellmer 0.4.0 is out now! New features include Claude caching & file uploads, support for newer OpenAI responses API, web search tools, and better security. Read more at tidyverse.org/blog/2025/11... #rstats