When @jameshwade.bsky.social mentioned hex stickers at our last #PositConf2026 speaker training, I realized I didn't have any for stbl.wrangle.zone, the #RStats 📦 I'm speaking about! Thankfully I had time to order a small batch. The url is unreadable, I'll have to fix that if I order another batch.

Coding agents can explore codebases. But you can't optimize them, compose them, or put them in a pipeline. RLMs can do all of that. They're DSPy modules, not agents. I built a shiny app to understand how they work.

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

My holiday project was building dsprrr, a package for declarative LLM programming in R, inspired by DSPy. The core idea is to treat LLM workflows as programs you can systematically optimize, not prompt strings you tweak by hand.

Introducing ensure, a new #rstats package for LLM-assisted unit testing in RStudio! Select some code, press a shortcut, and then the helper will stream testing code into the corresponding test file that incorporates context from your project. github.com/simonpcouch/...

Jumping on the #rstats "we're so back" train 🚂 Here's two fun (unrelated) things I scrolled upon tonight: 📊 tinyplot - base R plotting system with grouping, legends, facets, and more 👀 github.com/grantmcdermo... 🔎 openalexR - Clean API access to search OpenAlex docs.ropensci.org/openalexR/ar...

GitHub - grantmcdermott/tinyplot: Lightweight extension of the base R graphics system

Lightweight extension of the base R graphics system - grantmcdermott/tinyplot

github.com

Worst prank *ever*

Nicola Rennie@nrennie.bsky.social · 2y ago

If you're teaching R, or statistics, and you want your students to get more practice of data wrangling with "messy" data, you can use the {messy} package to turn the clean data you currently use for examples into more realistic looking data! #RStats #StatsEd

Having a hard time focusing on code today. Instead of refreshing news sites, tell me about an R package or function that made your life easier recently? I finally figured out how group_modify() works, and it's been a game-changer for some nested data madness. #rstats #dataBS

If you’ve been waiting try out LLMs with code, now is the time to do it.

Hadley Wickham@hadley.nz · 2y ago

A few things I've been working on lately: elmer, elmer.tidyverse.org, is a new package to make it easier to work with LLMs (hosted and local) from #rstats. It includes helps for structured data extraction and tool calling, and an easy way to upload a plot. Joint work with Joe Cheng.

The last Wednesday of each month I host a Workflow Demo with various Posit folks 💛 Tomorrow Oct 30th @ 11am ET Ryan Johnson will share how to use #Quarto & #Shiny to create #Typst PDFs dynamically 🎉 add to 🗓️: pos.it/team-demo I know it's during R/Pharma 😬 so please know it's recorded too!

You can now build a chatbot in shiny in less than 20 lines of code. shinychat and elmer make this much easier than it was even a month ago. elmer nails LLM abstractions. Go check them out if you haven't already!

I had fun giving a talk at #rpharma about how to integrate AI into your shiny apps. You can check out my talk here: jameshwade.github.io/r-pharma-talk/