Profile avatar
simonpcouch.com
he/him - writing statistical software at Posit, PBC (née RStudio)🥑 simonpcouch.com, @simonpcouch elsewhere
149 posts 3,248 followers 180 following
Prolific Poster
Conversation Starter

For those following the #rstats {ellmer} package: I got the chat_databricks() and chat_snowflake() providers working with tool calling this past week. IMHO this means these providers are no longer toys: they can be used with RAG (via {ragnar}) and other complex tasks like @simonpcouch.com's {btw}.

🚨 Big milestone for Rdatasets 🚨 The web archive now hosts 3400+ free and documented CSV datasets. Fantastic for teaching and testing! And {Rdatasets} is a new #RStats 📦 for easy download and search Web archive: vincentarelbundock.github.io/Rdatasets R 📦: vincentarelbundock.github.io/Rdatasetspkg

We are delighted to announce mirai 2.3.0 for advanced async computing in #RStats! Mirai allows event-driven async in Shiny & parallel processing in purrr. This release brings improvements in serialization & distributed computing. Read more from @shikokuchuo.net: shikokuchuo.net/posts/26-mir...

❗️Our next workshop will be on June 13th, 6 pm CEST, on Using LLMs with ellmer by @hadley.nz! Register or sponsor a student by donating to support Ukraine! Details: bit.ly/3wBeY4S Please share! #AcademicSky #EconSky #RStats

finetune::tune_race_anova is all you need

Friends, I have news. It is very good news. You'll just have to read it, I'm afraid. jamesclaims.substack.com/p/introducin...

I regret nothing yet! fly.io/blog/youre-a...

At Posit, we love @typst.app: ⚡ Make PDFs in milliseconds, not minutes ✨ The power of LaTeX with today's technologies ✍️ Modern typography (including emojis!) 🧠 Clear mental model So I'm thrilled to announce that we're now supporting its development: posit.co/blog/posit-a... #rstats

The Modern R Stack for Production AI: doi.org/10.59350/z9f... Python isn't the only game in town anymore: R can interact with local and cloud LLM APIs, inspect and modify your local R environment and files, implement RAG, computer vision, NLP, evals, & much more #Rstats

With so many LLMs available to help you write #RStats code, how do you choose the right one? We put a handful of models to the test using the vitals package, our framework for robust LLM evaluation. Check out the analysis on the Posit Blog! posit.co/blog/r-llm-e...

Say hello to kuzco, an LLM-powered computer vision assistant package in #RStats! @frankiethull.bsky.social's kuzco leverages Ollama to bring computer vision capabilities into your R workflow. Learn about classification, image recognition, and sentiment analysis in kuzco: posit.co/blog/kuzco-c...

I think MCP will be a big deal for a lot of folks in my orbit. Think of it as a way to constrain LLM output to more specifically match your needs & use cases. That could be better understanding your data, or focusing on a set of casual inference tasks supported by your favourite libraries.

Introducing acquaint, an R package that turns your R sessions into a Model Context Protocol (MCP) server. This allows MCP-enabled tools like Claude Desktop and Claude Code to run #rstats code _in your active R sessions_ to explore objects, read documentation, etc. posit-dev.github.io/acquaint/

Introducing the btw package for teaching LLM chat apps about your #RStats package! Inject "invisible" messages into chats via system prompts and use tool calls to dynamically fetch context when needed. Check out a dplyr example and learn more in @simonpcouch.com's post! posit.co/blog/custom-...

New on my blog: the Claude 4 models are here! I evaluate the new releases of Sonnet and Opus against Claude 3.7 Sonnet and o4-mini on a dataset of challenging #rstats coding problems. www.simonpcouch.com/blog/2025-05...

WHAAAAAAAAAATTTTTTTTTTTTTTTTTTTTTTTTTT

mirai - minimalist async framework for #RStats - released as an 'r-lib' package. Blog post: Advancing Async Computing in R. shikokuchuo.net/posts/26-mir... mirai provides event-driven async for #RShiny and parallel processing for purrr #tidyverse. Really excited to be working on this at Posit!

New on my blog: Google's Gemini 2.5 Pro release really made a splash last month. They've just announced an update to 2.5 Flash, a faster and cheaper model; I put it through its paces on challenging #rstats coding problems. www.simonpcouch.com/blog/2025-05...

✨Use llms from #rstats with ellmer ✨Version 0.2.0 is on CRAN now. No blog post yet because I'm about to go on vacation, but in the meantime you can check out the release notes: github.com/tidyverse/el....

Pope from Chicago All things go, all things go

Just made promptdown public. It's a plain-text interface for working with LLMs using literate programming. See and edit the full prompt each turn. No cramped input boxes, no hidden context, no append-only chat. Still early alpha, feedback welcome! github.com/t-kalinowski...

In only two years, ChatGPT has unraveled the entire academic project. James D. Walsh writes for @intelligencer.com: nymag.com/intelligence....

Hey, I recognize one of those logos.🙂 (Well, @ivelasq3.bsky.social did!)

New on my blog: The initial Gemini 2.5 Pro release a month ago was surprisingly strong, so I was excited to benchmark the model's update announced yesterday on #rstats coding problems. www.simonpcouch.com/blog/2025-05...

@hannahritchie.bsky.social's writing has really shaped my thinking about climate and sustainability over the years. Finding this new blog post from her on the carbon footprint of AI use quite informative: www.sustainabilitybynumbers.com/p/carbon-foo...

Thanks @dslc.io for using #TidyTuesday to highlight the unprecedented and likely illegal termination of >1000 #NSF grants in April. The #rstats, #python, and #dataBS community can help us understand and visualize the story of what's happening.

Stoooked for my first time attending userR!! Very much looking forward to finally meeting some internet friends. :) I'll be speaking about chores, an #rstats package that helps with repetitive but hard-to-automate tasks using LLMs.

stacks 1.1.0 is now on #rstats CRAN! stacks implements model ensembling for the tidymodels framework. This release introduces support for parallelism with the futureverse as part of our push to modernize tidymodels' parallelism support. github.com/tidymodels/s...

How do you foster a nuanced understanding of AI/LLMs at your organization? Posit's internal hackathons offer a compelling model: we get our team building with LLMs, leading to real understanding. @andrewholz.bsky.social explores lessons learned from this approach: posit.co/blog/llm-hac...

chores 0.2.0 is now on CRAN! chores provides an extensible library of LLM assistants for #rstats. This release makes the addin's UI more intuitive and makes it simpler to add custom prompts to the package. More on chores: posit.co/blog/introdu...