Simon P. Couch
@simonpcouch.com
he/him - writing statistical software at Posit, PBC (née RStudio)🥑 simonpcouch.com, @simonpcouch elsewhere
We've shipped Deepseek V4.1 Flash in Posit AI Pass! It's ~10x cheaper than Sonnet 5.5, very fast, and very capable. Unfortunately, it speaks Claude 5.0 Claude-ish, so I find its prose somewhat annoying to read. It can sometimes be overly thorough on simple tasks. assistant.posit.co/docs/getting...
A coffee break can make your next message to a coding agent more expensive. We explain how token caching works, how to check your costs, and how Posit Assistant helps keep your cache warm. Read here: https://opensource.posit.co/blog/2026-10-23_ai-newsletter/
Unfortunately, you need to care about token caching
Understanding the anatomy of an LLM 'conversation' can help you save money.
opensource.posit.co
Feel like too few people know how freaking good Posit Assistant is.
Simon P. Couch@simonpcouch.com · 3d agoWe've been working to make Posit Assistant as cost-efficient as possible. In our data science evals, Posit Assistant is now 18% cheaper than Claude Code and 25% cheaper than Codex, while performing similarly well or better than those two agents. opensource.posit.co/blog/2026-10...
We've been working to make Posit Assistant as cost-efficient as possible. In our data science evals, Posit Assistant is now 18% cheaper than Claude Code and 25% cheaper than Codex, while performing similarly well or better than those two agents. opensource.posit.co/blog/2026-10...
Posit Assistant is cost-efficient
Posit Assistant makes better use of your token budget than leading coding agents.
opensource.posit.co
commons agents prefer to answer data questions by invoking code that data scientists already trust and maintain--R/Python packages, Quarto docs, Shiny apps. If they can't find relevant code, they can fall back to writing SQL/R/Python "by hand," and that decrease in trust is signaled to the user.
Simon P. Couch@simonpcouch.com · 2mo agoWe're excited to share commons, an R and Python package that helps data scientists build trustworthy data agents for their organizations! Read more on the @posit.co open source blog: opensource.posit.co/blog/2026-09...
I made an AI video about genzplyr and I lowkey love it. It's also 100% slop. In this post I dig into what makes something slop, when it's ok to share it, and how to avoid it in work that matters. Read more at: substack.hadley.nz/p/what-is-slop
What is slop?
I made an AI video about genzplyr and I lowkey love it. It's also 100% slop. In this post I dig into what makes something slop, when it's ok to share it, and how to avoid it in work that matters.
substack.hadley.nz
New on the @posit.co open source blog: if you step away from your coding agent long enough to make a coffee, your next message could cost ~16x as much☕ @sara-altman.bsky.social and I wrote about token caching and AI costs: opensource.posit.co/blog/2026-10...
Unfortunately, you need to care about token caching
Understanding the anatomy of an LLM 'conversation' can help you save money.
opensource.posit.co
an outdated system in a salmon farm using PHP was found to have been breached, allowing the attackers to perform remote cod execution
i maintain that MLE for "ML engineer/ing" was mostly meant to provoke statisticians
JD Long@jdlong.cerebralmastication.com · 3w agoIt’s awesome that GLM is a LLM model name and a generalized linear model. Because there was not enough confusion in the ML space.
In case you weren't able to make it, @sara-altman.bsky.social and I wrote up the talk for the @posit.co OSS blog. We talked about the rise of "vibe analysis," the pitfalls of human-in-the-loop, and some new software from Posit. opensource.posit.co/blog/2026-10...
Correct, transparent, and reproducible data agents
An annotated walkthrough of our posit::conf(2026) keynote.
opensource.posit.co
Simon P. Couch@simonpcouch.com · 4w agoSuch an honor to keynote at posit::conf(2026). I still vividly remember the first conf keynote I ever saw, when @jennybryan.bsky.social spoke about debugging in San Francisco. Very grateful for the opportunity (especially to present alongside @sara-altman.bsky.social)!
“You are infringing on the time and brainpower of people by pushing "your" content that little/no of your brainpower went into” is such a banger
Kybosh@kybosh.bsky.social · 4w agoI like seeing the dev of the SNES core on the Pocket actually telling one of these dudes off. Holy shit.
Such an honor to keynote at posit::conf(2026). I still vividly remember the first conf keynote I ever saw, when @jennybryan.bsky.social spoke about debugging in San Francisco. Very grateful for the opportunity (especially to present alongside @sara-altman.bsky.social)!
Some reflections on one of the first #rstats packages I wrote: simonpcouch.com/blog/2026-10...
Software is so cool | Simon P. Couch
Reflecting on one of my earlier software projects.
simonpcouch.com
A pair of boring odbc patch releases have made their way to CRAN in the past couple weeks🥱 Hopefully they make R database users' lives easier! github.com/r-dbi/odbc/r...
Releases · r-dbi/odbc
Connect to ODBC databases (using the DBI interface) - r-dbi/odbc
github.com
New in querychat: multiple tables, chat history, data-dict, and easy extraction of findings into Quarto, Shiny, Jupyter, etc. querychat is now much more capable beyond just querying "pre-defined" Shiny outputs. Available for both #rstats and #python. opensource.posit.co/blog/2026-09...
FYI Posit AI Pass subscribers; we wound down the instance serving Gemma 4 today. If you were a regular user, you might give GLM 5.3 Flash a try; it's vision capable, quite a bit larger and newer (and thus more capable!), and served at ~half the price that Gemma 4 was per-token!
Wicked psyched to share that shinychat v0.5.0 #RStats and v0.7.1 #Python are now available! Check out all the rad new features on the Posit Open Source blog. #PositConf2026 opensource.posit.co/blog/2026-09...
Complete chat applications in shinychat: R 0.5.0 and Python 0.7.1
shinychat v0.5.0 for R and v0.7.1 for Python make it easier to build complete, conversation-centered Shiny chat applications with history, editing, branching, greetings, suggestions, citations, tool d...
opensource.posit.co
Every time @simonpcouch.com makes a great point in his #positconf2026 Keynote, his earring sparkles extra brightly in the stage lights. 🌟
We're excited to share commons, an R and Python package that helps data scientists build trustworthy data agents for their organizations! Read more on the @posit.co open source blog: opensource.posit.co/blog/2026-09...
In this edition of My Coworkers Are Awesome, @hadley.nz had a real-life version of the blob on the chores sticker made!
#PositConf2026 (via the #RPharmaSummit2026 pre-game) has already been worthwhile for introducing me to Kimi K3 in Posit AI Pass! So far it's good, fast, and relatively cheap. This is what I get for skipping any of @simonpcouch.com 's blog posts! opensource.posit.co/blog/2026-08...
Kimi K3 and GLM 5.2 are now in Posit AI
A new batch of open weights models in Posit AI show impressive capabilities at a fraction of the price.
opensource.posit.co
What a lineup!
LatinR Conf@latinrconf.bsky.social · 2mo ago🎉 Se vienen los tutoriales de LatinR 2026: Quarto+GH Actions, slides con revealjs, LLMs con {ellmer}, tidymodels, tu primer paquete de R y Shiny+ellmer. Inscripción abierta (early bird hasta el 4/10) 👉 latinr.org/blog/es/2026... #LatinR2026 #RStats
"For a while, I must admit, it looked as if software developer roles like mine were done for. [...] But our industry is slowly realizing that making truly cutting-edge software still requires humans to think and work together, to maximize their skill sets and to practice their respective crafts."
Paul Ford@ftrain.com · 2mo agoEveryone else is worried about the AI apocalypse but I’ve been hearing about that for 30 years and I can’t get very worked up any more. For me the question is: If these things can code (and they can!) then why aren’t we seeing any great software? www.nytimes.com/2026/09/12/o...
RUN ML MODELS DIRECTLY IN YOUR DATABASE
Emil Hvitfeldt@emilhvitfeldt.bsky.social · 2mo agoHere is next release of R-orbital and tidypredict! The take away from this release is that we massively expanded the supported models, With this release we are able to support all tabular models that can be supported from tidymodels opensource.posit.co/blog/2026-09... #rstats #tidymodels #databs
posit.co/conference is next week! So stoked! We got an order in for a Houston limited edition (ruby red grapefuit!) #rstats stacks sticker just in time. :)
Can't make it to Houston? Virtual passes for posit::conf(2026) start at $99, with academic and nonprofit rates at $49 and a needs-based option at $0. Every keynote and session livestreamed, September 14–16. conf.posit.co
New on the @posit.co blog: In my experience, fine tuning LLMs is more difficult and more expensive than I've seen it made out to be. In most cases, I'd recommend focusing your efforts on experimenting with a bunch of prompts and existing models. opensource.posit.co/blog/2026-09...
AI Newsletter: You probably don't want to fine-tune
You're usually better off doing plain old prompt engineering.
opensource.posit.co
5 months ago, models in the ~30B A3B range started to be able to do simple agentic coding tasks. I recently wondered how 8B (or even 4B!) models would fare: simonpcouch.com/blog/2026-09...
