Simon P. Couch
@simonpcouch.com
he/him - writing statistical software at Posit, PBC (née RStudio)🥑
simonpcouch.com, @simonpcouch elsewhere
simonpcouch.com, @simonpcouch elsewhere
Reposted by Simon P. Couch
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
It's called shinymcp. Drop-downs, plots, tables all inline in the chat.
github.com/jameshwade/shinymcp
February 8, 2026 at 7:53 PM
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
It's called shinymcp. Drop-downs, plots, tables all inline in the chat.
github.com/jameshwade/shinymcp
Reposted by Simon P. Couch
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.
But "it doesn't work and is fake" is just wrong now.
February 2, 2026 at 3:38 AM
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.
But "it doesn't work and is fake" is just wrong now.
Reposted by Simon P. Couch
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
Feb 3 @ 12 pm ET: pos.it/dslab
February 2, 2026 at 3:09 PM
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
Feb 3 @ 12 pm ET: pos.it/dslab
Reposted by Simon P. Couch
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 grfp@grant-witness.us so we can compile + follow up
Details and template at grant-witness.us/grfp-letter
1) Write NSF
2) Write your Congressperson
3) CC us at grfp@grant-witness.us so we can compile + follow up
Details and template at grant-witness.us/grfp-letter
February 2, 2026 at 5:58 PM
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 grfp@grant-witness.us so we can compile + follow up
Details and template at grant-witness.us/grfp-letter
1) Write NSF
2) Write your Congressperson
3) CC us at grfp@grant-witness.us so we can compile + follow up
Details and template at grant-witness.us/grfp-letter
Reposted by Simon P. Couch
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...
www.simonpcouch.com/blog/2026-01...
February 1, 2026 at 6:48 PM
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...
www.simonpcouch.com/blog/2026-01...
Reposted by Simon P. Couch
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.
🗞️ Here's the latest edition of the Posit AI newsletter, your biweekly roundup of AI news from Posit and beyond.
This week's edition includes:
• Claude's "constitution"
• How much electricity do coding agents use?
• Pre- and post-training
And more!
📬 Read the newsletter: posit.co/blog/ai-news...
This week's edition includes:
• Claude's "constitution"
• How much electricity do coding agents use?
• Pre- and post-training
And more!
📬 Read the newsletter: posit.co/blog/ai-news...
AI Newsletter 2026-01-30 - Posit
Claude's constitution, how much power does Claude Code use, and LLM plot interpretation
posit.co
January 30, 2026 at 7:38 PM
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...
More on @sara-altman.bsky.social and I's bluffbench eval: posit.co/blog/llm-plo...
January 28, 2026 at 3:06 PM
"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...
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...
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...
January 26, 2026 at 3:38 PM
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...
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:
January 26, 2026 at 2:00 PM
Heck of a weekend. Timeline cleanse from the local sledding hill:
Reposted by Simon P. Couch
Imagine what’s happening in the camps.
Imagine how much they’d be lying about what happened without all the videos showing it from multiple angles.
January 24, 2026 at 11:29 PM
Imagine what’s happening in the camps.
Reposted by Simon P. Couch
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
Maybe someday I'll make a longer, more official blog post showing glance() vs. model_performance() and augment() vs. marginaleffects::predictions() 🤷♂️ #rstats #easystats
January 23, 2026 at 4:37 PM
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
Maybe someday I'll make a longer, more official blog post showing glance() vs. model_performance() and augment() vs. marginaleffects::predictions() 🤷♂️ #rstats #easystats
Reposted by Simon P. Couch
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...
posit.co/blog/llm-plo...
LLMs interpret plots well, until expectations interfere - Posit
posit.co
January 22, 2026 at 11:57 PM
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...
posit.co/blog/llm-plo...
Reposted by Simon P. Couch
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...
@simonpcouch.com and I investigated why and what might help: posit.co/blog/llm-plo...
January 22, 2026 at 9:31 PM
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...
@simonpcouch.com and I investigated why and what might help: posit.co/blog/llm-plo...
Reposted by Simon P. Couch
ICE kidnapped a 5-year-old and sent him alone to a facility in Texas. Hell isn't hot enough.
January 21, 2026 at 11:14 PM
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...
On my blog: www.simonpcouch.com/blog/2026-01...
January 20, 2026 at 2:38 PM
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...
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...
posit.co/blog/2026-01...
January 16, 2026 at 4:53 PM
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...
posit.co/blog/2026-01...
Reposted by Simon P. Couch
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...
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...
Semi-automating 200 Pull Requests with Claude Code – Davis Vaughan
blog.davisvaughan.com
January 12, 2026 at 1:42 PM
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...
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...
Reposted by Simon P. Couch
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...
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...
Privacy and AI Assistants - Posit
Many of our LLM tools can execute code and access your files. What does this mean for privacy?
posit.co
January 8, 2026 at 3:10 PM
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...
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...
Reposted by Simon P. Couch
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.
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.
January 7, 2026 at 3:00 AM
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.
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.
Reposted by Simon P. Couch
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
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
skills/r-lib/testing-r-packages at main · posit-dev/skills
A collection of Claude Skills from Posit. Contribute to posit-dev/skills development by creating an account on GitHub.
github.com
December 24, 2025 at 12:50 PM
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
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
Reposted by Simon P. Couch
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?
I just published Potato, a new pansharpening package. It aims to render certain kinds of satellite imagery more clearly and accurately than what’s for sale and on satellite maps today: github.com/celoyd/potato/
GitHub - celoyd/potato: A small pansharpening model
A small pansharpening model. Contribute to celoyd/potato development by creating an account on GitHub.
github.com
December 23, 2025 at 10:49 PM
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?
Reposted by Simon P. Couch
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! 🧑🎄
December 23, 2025 at 4:40 PM
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! 🧑🎄
Reposted by Simon P. Couch
Context windows out to thwart all our beautiful dreams
December 22, 2025 at 5:23 PM
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...
posit.co/blog/2025-12...
2025-12-19 AI Newsletter - Posit
In this edition of the Posit AI Newsletter, we dive into the most important AI news and research from the past two weeks. Curated for the data science community, we cover everything from model updates...
posit.co
December 19, 2025 at 5:51 PM
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...
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...
Read more: github.com/tidymodels/i...
December 18, 2025 at 2:27 PM
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...
Read more: github.com/tidymodels/i...