Simon P. Couch
LightNews LightNews
banner
simonpcouch.com
Simon P. Couch
@simonpcouch.com
3.4K followers 190 following 200 posts
he/him - writing statistical software at Posit, PBC (née RStudio)🥑

simonpcouch.com, @simonpcouch elsewhere
Posts Replies Media Videos
simonpcouch.com
side::kick() is model-agnostic. When you first launch the app, a setup flow will detect whether any common providers are already configured to help you get started.

#rstats
November 7, 2025 at 12:48 PM
simonpcouch.com
I'm excited to share side::kick(), an experimental open-source coding agent for RStudio built entirely in R. It can interact with your files, communicate with your active #rstats session, and run code.

Check it out: github.com/simonpcouch/...
November 5, 2025 at 3:57 PM
simonpcouch.com
I'll be keynoting at R/Pharma a week from today! The conference is free and virtual. I'll be focused on the mundane use cases of LLMs for wrangling data with #rstats, and the content should feel applicable for folks outside of pharma—come through. :)

Register: events.zoom.us/ev/Ai-geyS63...
A title slide reading "Practical AI for data science" and my name and title.
October 29, 2025 at 7:32 PM
simonpcouch.com
I sincerely apologize for the mcptools package not having a cute lil feller on its hex sticker in its first release. This will be corrected in the next #rstats CRAN release!!!

posit-dev.github.io/mcptools/
A before-and-after comparison of hex logo designs for "mcptools". The "Before" panel features a serene landscape with a wooden bridge over water, surrounded by trees, flowers, and mountains in muted tones. The "After" panel presents a vibrant, cartoon-style jungle scene with a cheerful monkey hanging from a rope bridge above a waterfall, holding a wooden sign that reads "mcptools", with colorful flowers and lush greenery throughout.
October 28, 2025 at 6:25 PM
simonpcouch.com
ICYMI, @sara-altman.bsky.social and I have been writing a biweekly newsletter on AI and open source data science on the @posit.co blog!

A bit about how that came to be on my #rstats blog: www.simonpcouch.com/blog/2025-10...
A screenshot of the Posit Blog homepage showing statistics (936+ posts, 22+ categories, 386+ tags) and two featured blog post cards. Both posts are AI Newsletter roundups from September 2025 by Sara Altman and myself, featuring AI-related R package hexes in their hero images.
October 8, 2025 at 1:16 PM
simonpcouch.com
Just dropped a WHOLE BUNCH of these somewhere👀👀👀

#positconf2025
A picture of a stack of hex stickers for the stacks package. The stickers have a tan and orange peaches & cream theme rather than the usual blueberry.
September 18, 2025 at 3:21 PM
simonpcouch.com
Just wrapped up a talk at #positconf2025 about LLM evaluation with R! Such a joy to hang out with #rstats folks in person and hear about what others are working on.

Resources and slides: github.com/simonpcouch/...
A chat interface showing a conversation starting with a user saying "Are there any talks about evals" and a response "Yes, Simon Couch just gave one, and he hopes you enjoyed it." There's a teddy bear mascot wearing a teal shirt and cap in the bottom right corner of the chat window. A picture from the side of a conference session room, with myself standing in front.
September 17, 2025 at 7:08 PM
simonpcouch.com
@sara-altman.bsky.social and I just shared the second release of the Posit AI Newsletter! In this edition, a landmark settlement on LLM training data and copyright, the emergence of agentic browsers, and more.

Read and subscribe on the Posit Blog: posit.co/blog/2025-09...
A graphic displaying, on the left, three robot icons, and on the left, a selection of LLM-related R package hex stickers.
September 12, 2025 at 4:10 PM
simonpcouch.com
So stoked to share about the first release of the Posit AI Newsletter!

@sara-altman.bsky.social and I have been working on a pilot of this newsletter internally for a few months now—an opinionated and pragmatic snapshot of AI news released every two weeks.

First edition: posit.co/blog/2025-08...
A graphic displaying, on the left, three robot icons, and on the left, a selection of LLM-related R package hex stickers.
August 29, 2025 at 3:01 PM
simonpcouch.com
In working on an eval for an experimental tidymodels AI assistant, I realized that today's frontier LLMs know much more about #rstats tidymodels than I thought.

www.simonpcouch.com/blog/2025-08...
A ggplot2 bar plot. On the x axis are two LLMs, Claude Sonnet 4 and Gemini Pro 2.5. Both bars are dodged by three configurations: Predictive, Databot, and `run_r_code()` tool. On the y axis is relative performance, ranging from 0 (baseline model) to 100 (best human modelers). The bar heights for Claude Sonnet 4 are all about the same (around 80) and, for Gemini 2.5 Pro, the height for Predictive, an app designed specifically as a tidymodels assistant, is much lower (around 20).
August 26, 2025 at 6:42 PM
simonpcouch.com
The limited run of the #rstats stacks hex for this year's posit::conf is confirmed🥞🥞🥞 I'll have a batch of peaches & cream stickers, come say hi to pick one up!

posit.co/conference/
Variants of the hex logo for the stacks package from different posit::conf years, each featuring a stack of pancakes with different toppings and color schemes. The 2025 version (top left) has orange colors with peach slices, 2024 (top right) uses dark blue/purple with blackberries, 2023 (bottom left) features red/pink with raspberries, and the original (bottom right) displays teal/blue with blueberries.
July 25, 2025 at 2:38 PM
simonpcouch.com
Drawing comparisons to Deepseek, a little-known company dropped an open-weights LLM Kimi K2 on Friday with some very impressive benchmarks. I tried it out and the vibes were bad.

www.simonpcouch.com/blog/2025-07...
A horizontal bar chart comparing various AI models' performance on R coding tasks. The chart shows percentages of correct (blue), partially correct (beige), and incorrect (orange) answers. Models listed from top to bottom are Kimi K2, Claude 4 Opus, Claude 4 Sonnet, GPT 4.1, GPT 4.1-mini, and Gemini 2.5 Flash. Claude 4 Opus shows the highest proportion of correct answers at approximately 60%, while Kimi K2 sits around 36%.
July 14, 2025 at 4:04 PM
simonpcouch.com
I've been getting a lot more out of Claude Code after hooking it up to tools that let it read #rstats pkg docs. I just type "read about some::topic" before tasking Claude with things that are unlikely to be in its training data, and the model will pull up whatever help files it needs.
June 11, 2025 at 2:15 PM
simonpcouch.com
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/
May 28, 2025 at 3:43 PM
simonpcouch.com
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...
A horizontal bar chart comparing various AI models' performance on R coding tasks. The chart shows percentages of correct (blue), partially correct (beige), and incorrect (orange) answers. Claude 4 Opus has the highest proportion of correct answers, followed by o4-mini, Claude 4 Sonnet, and Claude 3.7 Sonnet.
May 27, 2025 at 3:48 PM
simonpcouch.com
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...
A horizontal bar chart comparing various AI models' performance on R coding tasks. The chart shows percentages of correct (blue), partially correct (beige), and incorrect (orange) answers. Gemini 2.5 Flash demonstrates performance somewhere between 2.5 Pro and o4-mini, with thinking resulting in a 10% increase in the proportion of correct answers. Claude 3.7 Sonnet and o4-mini remain the top performers.
May 21, 2025 at 4:27 PM
simonpcouch.com
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...
A horizontal bar chart comparing various AI models' performance on R coding tasks. The chart shows percentages of correct (blue), partially correct (beige), and incorrect (orange) answers. The new Gemini 2.5 Pro shows roughly comparable performance to its previous generation, both of which lag behind Claude 3.7 Sonnet and GPT o4-mini.
May 7, 2025 at 3:24 PM
simonpcouch.com
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...
The package logo, a small yellow blob happily holding a clipboard.
April 30, 2025 at 3:41 PM
simonpcouch.com
New on my blog: With a pair of coding-focused model drops, it's clear OpenAI is aiming for the developer market. How well do the newest o3 and o4-mini perform on #rstats coding tasks?

www.simonpcouch.com/blog/2025-04...
A horizontal bar chart comparing various AI models' performance on R coding tasks. The chart shows percentages of correct (blue), partially correct (beige), and incorrect (orange) answers. Models are grouped into non-reasoning and reasoning categories. OpenAI's newest models (o3, o4-mini) show slightly stronger performance than Claude 3.7 Sonnet (both with and without thinking enabled).
April 18, 2025 at 3:44 PM
simonpcouch.com
New on my blog: OpenAI dropped a trio of models yesterday that they claim result from "focusing closely on real-world developer needs." I was curious whether this might mean stronger #rstats coding performance.

www.simonpcouch.com/blog/2025-04...
A ggplot2 bar plot showing the counts of correct, partially correct, and incorrect answers from various LLMs on R coding problems. Claude Sonnet 3.7, shown in orange, answer questions correctly much more often than the GPT series models, shown in shades of blue. GPT-4o answers questions correctly less often than any of the GPT 4.1 series models.
April 15, 2025 at 3:49 PM
simonpcouch.com
New on my blog: I've been seeing lots of hype claiming that Gemini 2.5 Pro is the new state of the art since the model's release last week. How well does it know #rstats?
www.simonpcouch.com/blog/2025-04...
A ggplot2 bar plot showing the counts of correct, partially correct, and incorrect answers from various LLMs on a dataset of R coding problems. Generally, Gemini Pro 2.5, o3-mini High, and Claude Sonnet 3.7 get around half of the problems correct. Gemini 2.0 Flash is more like a third.
April 2, 2025 at 3:52 PM
simonpcouch.com
odbc 1.6.0 is now on #rstats CRAN! Includes a new helper for Redshift, a hex sticker (finally!), and many QOL improvements for Databricks, Snowflake, MSSQL, etc.

Read more: odbc.r-dbi.org/news/index.h...
A hexagonal sticker with an all black background and "odbc" written in layered shades of blue.
March 4, 2025 at 3:24 PM
simonpcouch.com
New #rstats pkg chores on CRAN!

chores is an extensible collection of LLM assistants for R to help you with repetitive, hard-to-automate tasks.

Read more: simonpcouch.github.io/chores/
February 24, 2025 at 2:35 PM
simonpcouch.com
New #rstats pkg gander is now on CRAN!

gander is a coding assistant that knows how describe the objects in your global R environment. So, when you're working with data, LLMs will know the names, types, and distributions of data columns, resulting in much more effective completions.
February 20, 2025 at 6:33 PM
simonpcouch.com
Around this time tomorrow I'll be giving a free, virtual talk for the Salt Lake City R User Group focused on 4 optimizations you can make to your #rstats code to drastically cut down on the time to train machine learning models. Please do come by.🏎️

Learn more: www.meetup.com/slc-rug/even...
A hero image for the slide deck. The title reads "From hours to minutes: accelerating your tidymodels code" and a tiled hex wall shows stickers for tidymodels packages rsample, recipes, parsnip, tune, and yardstick.
January 27, 2025 at 5:05 PM