iiinova — where your digital self keeps evolving

Simon P. Couch @simonpcouch.com · 16/09/2026

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!

071

Reposted by Simon P. Couch

Kelly Bodwin @kellybodwin.com · 15/09/2026

Every time @simonpcouch.com makes a great point in his #positconf2026 Keynote, his earring sparkles extra brightly in the stage lights. 🌟

Simon Couch on stage, next to a projected slide showing an article title from Science journal warning about software errors.

1182

Simon P. Couch @simonpcouch.com · 15/09/2026

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...

A screenshot of the blog post announcing commons. The hero image shows the hex sticker, a common kingfisher on a park bench.

14311

Simon P. Couch @simonpcouch.com · 14/09/2026

In this edition of My Coworkers Are Awesome, @hadley.nz had a real-life version of the blob on the chores sticker made!

Me, happily holding a plushie of a small blob holding a clipboard.

0411

Reposted by Simon P. Couch

Jon Harmon (he/him/his) @jonthegeek.com · 13/09/2026

#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...

opensource.posit.co

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.

131

Reposted by Simon P. Couch

Simon Willison @simonwillison.net · 12/09/2026

"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."

512521

Simon P. Couch @simonpcouch.com · 11/09/2026

I AM SO EXCITED FOR POSIT CONF

2223

Reposted by Simon P. Couch

Grace @gracekind.net · 10/09/2026

Crossposting to the swarm artifactory instance

2651

Simon P. Couch @simonpcouch.com · 09/09/2026

RUN ML MODELS DIRECTLY IN YOUR DATABASE

0156

Simon P. Couch @simonpcouch.com · 08/09/2026

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. :)

Five hexagonal stickers for the 'stacks' R package from tidymodels.org, each featuring an illustration of a stack of pancakes with syrup and different fruit toppings. The word 'stacks' is arranged in a descending staircase pattern on each hex. The top-left 'Original' version has a light blue background with a steel blue border and blueberry topping. The top-right 'posit::conf(2026)' version has a burnt orange background with a dark brown border and grapefruit slices. The bottom row shows three more conference editions: 'posit::conf(2025)' in cream with a copper border and peach slices, 'posit::conf(2024)' in muted purple with a dark navy border and blackberries, and 'posit::conf(2023)' in soft pink with a rose-red border and strawberries.

1183

Reposted by Simon P. Couch

Posit @posit.co · 07/09/2026

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

1257

Simon P. Couch @simonpcouch.com · 04/09/2026

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...

opensource.posit.co

AI Newsletter: You probably don't want to fine-tune

You're usually better off doing plain old prompt engineering.

2225

Simon P. Couch @simonpcouch.com · 03/09/2026

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...

Agentic coding reliability for five recent local models. Granite 4.2 8B succeeded in 80 percent of runs and Ornith 1.5 9B in 60 percent. Granite 4.2 3B, LFM 2.5 2.6B, and Qwen 3.8 4B Distill all scored zero.

061

Reposted by Simon P. Couch

Garrick Aden-Buie @grrrck.xyz · 02/09/2026

GLM 5.3 Flash is really fun. Super zippy and super cheap, and it’s great at getting things done. Pair it with a smart model or a smart human and you can get places fast!

0102

Simon P. Couch @simonpcouch.com · 02/09/2026

We just shipped GLM 5.3 and GLM 5.3 Flash in Posit AI Pass! GLM 5.3 Flash is now the cheapest model available via the subscription (half the price of Gemma 4 26B A4B per-token!) and I've been so, so impressed with it. GLM 5.3 is Ox Alpha, the anonymous model that was popping off on OpenRouter.

Table comparing AI model costs per token, sorted from cheapest to most expensive. Columns: Model, Lab, and Relative Cost Per-Token. GLM 5.3 Flash (Z.ai) is cheapest at 0.05x; Gemma 4 26B (Google, going away soon) at 0.1x; Claude Haiku 4.5 (Anthropic, going away soon) at 0.33x; GLM 5.3 (Z.ai) and GLM 5.2 (Z.ai, going away soon) both at 0.38x; Claude Sonnet 5 (Anthropic) at 0.67x; Claude Sonnet 4.6 (Anthropic) at 1x as the baseline; Kimi K3 (Moonshot AI) at 1x; and Claude Opus (Anthropic) as the most expensive at 1.67x.

1142

Simon P. Couch @simonpcouch.com · 17/08/2026

How do you choose an LLM? A survey of the current model landscape, including results from the vibes-from-Sara-and-Simon eval (/s) New on the @posit.co open source blog: opensource.posit.co/blog/2026-08...

opensource.posit.co

AI Newsletter: How to choose a model

Which model is 'best'? A survey of the current model landscape.

1103

Simon P. Couch @simonpcouch.com · 10/08/2026

I've been really impressed with Kimi K3 and GLM 5.2 the last couple weeks. I'm excited to share that we've made the models available in Posit AI with strong privacy guarantees and a steep discount compared to the Claude models currently available in the service! opensource.posit.co/blog/2026-08...

opensource.posit.co

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.

0335

Simon P. Couch @simonpcouch.com · 05/08/2026

i was looking up song lyrics and

Screenshot of a Google search for "don't mean to wake you up." The AI Overview box responds: "You are not disturbing anything. I am ready to help you right now," followed by a "How to Proceed" section suggesting the user share a question, topic, or task, and asking "What would you like to work on today?" Below the AI Overview is a "Show more" expander, then a YouTube search result for Ken Yates' song "Don't Mean To Wake You (Acoustic)."

081

Simon P. Couch @simonpcouch.com · 03/08/2026

Data analysis is often a branching and nonlinear process. We just shipped a feature in Posit Assistant to help with this; use /eda-log to keep track of loose ends in your analysis. @posit.co #databs #rstats opensource.posit.co/blog/2026-07...

opensource.posit.co

AI Newsletter: EDA log in Posit Assistant

A higher-level view of your data analysis conversations.

0254

Reposted by Simon P. Couch

Max kuhn @topepo.bsky.social · 29/07/2026

We're happy to announce our new #rstats package: lorax. If you fit tree-based models, lorax enables conversion to the party package's format (for making nice tree diagrams) and has methods to compute which features were used, the number of terminal nodes, etc. opensource.posit.co/blog/2026-07...

opensource.posit.co

Introducing lorax: Speaking for the Tree-Based Models

lorax is a new R package that characterizes fitted tree- and rule-based models: extract their decision rules, see which predictors they actually use, and convert trees for plotting with partykit.

26112

Reposted by Simon P. Couch

Carlos Scheidegger @cscheid.net · 28/07/2026

I am begging you to talk to other human beings directly, and not through a Claude layer. This goes doubly when I ask you, directly, to talk to me not through a Claude layer. Please.

2474

Reposted by Simon P. Couch

Hadley Wickham @hadley.nz · 24/07/2026

This week on my substack: a write up of my talk "y code when ai" (my thoughts on why knowing how to code is still relevant), along with a brief description of how I turned a video of my talk into this post. Read it at open.substack.com/pub/tidydesi... !

open.substack.com

y code when ai?

A talk on AI and coding

2477

Reposted by Simon P. Couch

Jeremy Allen @jeremy-data.bsky.social · 24/07/2026

It’s Friday. Do a breakthrough.

3173

Reposted by Simon P. Couch

Tomasz Kalinowski @t-kalinowski.bsky.social · 23/07/2026

I'm happy to share `ir`, a new command-line tool for running portable R scripts and Quarto documents. It's inspired by my two favorite parts of `uv`: self-describing scripts and tools you can run without installing first. opensource.posit.co/blog/2026-07...

opensource.posit.co

ir 0.1.0: self-describing R scripts and Quarto documents

`ir` is a new command-line tool for running portable R scripts and rendering Quarto documents whose package requirements, and optional R selection, live inside the file itself.

47521

Simon P. Couch @simonpcouch.com · 21/07/2026

Just ran today's Gemini 3.6 Flash release through #rstats bluffbench2. In the ballpark of Gemini 3.5 Flash on performance, slightly (5-10%) cheaper. More on the eval: posit-dev.github.io/bluffbench2/

A bar plot showing scores for several frontier models. The two leaders, Gemini 3.5 Flash and Claude Fable 5, score in the mid-high teens. Gemini 3.6 Flash is around 10%. Models from OpenAI cluster at the bottom, never eclipsing 10%.

070

Simon P. Couch @simonpcouch.com · 21/07/2026

One of the more interesting findings to me from this eval is that prematurely adding modeled results (like #rstats geom_smooth()) to plots drastically reduces the chances that models will catch the issue in the plot.

A dumbbell plot, one row per model, comparing accuracy on artifact plots the model drew with a geom_smooth() overlay versus without. For nearly every model the 'with overlay' point sits well to the left of the 'without' point; Claude Fable 5 falls from about a quarter correct to zero, and Gemini 3.5 Flash from about a quarter to under a tenth.

170

Simon P. Couch @simonpcouch.com · 18/07/2026

Was poking around rstudio.org in the Wayback Machine and came across this feature release from April 2011 (the second release of the IDE!)... `manipulate()` "enables you to create plots with inputs bound to custom controls (e.g. slider, picker, etc.)" #rstats

Blog post header reading 'RStudio Beta 2 (v0.93),' posted April 11, 2011 in News by jjallaire with 32 comments. The opening text announces that RStudio Beta 2 is available for download and reflects feedback from the R community, with a link to the release notes for full details.

Section titled 'Interactive Plotting' describing manipulate, a new feature for creating plots with inputs bound to custom controls like sliders, pickers, and checkboxes instead of fixed values. Below the description is an R code example using manipulate() to plot the 'cars' dataset with an x.max slider, a type picker (Points/Line/Step), and a Draw Labels checkbox. A screenshot shows this in action within RStudio: a 'Manipulate' control panel on the left with an x.max slider set to 25, a 'type' dropdown set to Points, and a checked 'Draw Labels' box, alongside a scatterplot of distance versus speed on the right.

3110

Simon P. Couch @simonpcouch.com · 17/07/2026

We're excited to share bluffbench2, a next-generation data science LLM evaluation. The eval measures how well models notice subtle data quality issues in plots. Even the most capable models today score in the mid-teens. opensource.posit.co/blog/2026-07...

opensource.posit.co

AI Newsletter: LLMs often miss subtle visual artifacts in data visualizations

Introducing bluffbench2, a new data science LLM evaluation.

1296

Reposted by Simon P. Couch

Grace @gracekind.net · 16/07/2026

This must mean that vibe-coded UIs were common in the human ancestral environment

744950

Reposted by Simon P. Couch

Hadley Wickham @hadley.nz · 14/07/2026

httr2 1.3.0 is out now! Includes a bunch of improvements to OAuth token caching and summarises some of the biggest changes in the last few patch releases — opensource.posit.co/blog/2026-07.... #rstats

opensource.posit.co

httr2 1.3.0

httr2 1.3.0 changes how OAuth tokens are cached on disk — you'll need to re-authenticate once after upgrading — and rolls up faster streaming, OAuth server metadata discovery, OpenTelemetry tracing, a...

0366

Reposted by Simon P. Couch

Pam Herd @pamherd.bsky.social · 14/07/2026

Key point with this piece is that Mandami is pushing back against the McKinsey approach to governing. Alondra Nelson actually put this best: "How a City interacts with its people shouldn’t be outsourced. It should be local and accountable."

Done right, digital government can help millions of people save hundreds of millions of dollars, and hours and hours of time. Done wrong, it can be costly, useless, discriminatory or even dangerous. How a City interacts with its people shouldn’t be outsourced. It should be local and accountable.

5766173

Reposted by Simon P. Couch

Libby Heeren @libbyheeren.bsky.social · 13/07/2026

Have you met Max Kuhn yet? If you've used {caret} or {tidymodels}, you probably KNOW who he is... but have you MET him?! Come hang with us this Thursday & meet the dude yourself! Register at pos.it/dsh if you haven't already, & we'll see you Thur July 16 @ 12PM ET #rstats #BrandonSanderson #iykyk

1131

Reposted by Simon P. Couch

isabel z @isabelizimm.bsky.social · 08/07/2026

The latest release of Positron leverages `uv` to make getting started with Python as easy as a single click 👾 I wrote up a lil blog post on the places Positron elevates `uv` to help with Python workflows. You can read it here: opensource.posit.co/blog/2026-07...

opensource.posit.co

Positron + uv: Python setup in one click

Exploring the Positron features that use uv to enable Python installation and management.

14211

Reposted by Simon P. Couch

Grace @gracekind.net · 07/07/2026

a lotta yall still dont get it Jevons holders can use multiple paradoxes on a single Jevon so if you have 1 Jevon and 3 paradoxes you can create 3 new Jevons

1417317

Simon P. Couch @simonpcouch.com · 06/07/2026

mcptools 1.0.0, an R SDK for the Model Context Protocol, is now on #rstats CRAN! This release introduces complete auth support for remote MCP servers, deployment on Posit Connect, and images in tool results. opensource.posit.co/blog/2026-07...

opensource.posit.co

mcptools 1.0.0

The first major release of mcptools, an R SDK for the Model Context Protocol, is now on CRAN.

1132

Reposted by Simon P. Couch

Hadley Wickham @hadley.nz · 02/07/2026

A coding agent is only useful if it can run whatever code the task demands, but a tool that runs arbitrary code is just as dangerous as it sounds! So how do you stop an agent from making mistakes you can't easily undo? Read more at: tidydesign.substack.com/p/help-my-co...

tidydesign.substack.com

Help! My coding agent can run code

A coding agent is only actually useful if it can run whatever code the task demands, but a tool that runs arbitrary code is just as dangerous as it sounds! So how do you protect ourself with guardrail...

3357

Reposted by Simon P. Couch

James Balamuta @coatless.bsky.social · 02/07/2026

Turn a Shiny app into a desktop app your users just double-click. shinyelectron wraps #rstats or #Python Shiny in Electron and builds a native installer for macOS, Windows, and Linux, with a runtime of your choice (including a fully offline build). Build locally or in CI. #rshiny #pyshiny

macOS drag-to-install window for demo-r-app-suite: the app icon with an arrow pointing to the Applications folder.

The app's About panel showing the r-shinylive (WebR) backend, R 4.6.0, 37 packages, platform wasm32-unknown-emscripten, inside the desktop app.

shinyelectron launcher listing three R Shiny apps as cards (Dashboard, Data Explorer, About), with an "Apps → Back to Launcher" menu open.

GitHub Actions run "Build demo installers" for shinyelectron 0.2.0, matrix building 73 of 76 jobs across macOS, Windows, and Linux.

3729

Simon P. Couch @simonpcouch.com · 03/07/2026

How do you customize the behavior of coding agents like Claude Code, Codex, or Posit Assistant? New on the @posit.co open source blog: opensource.posit.co/blog/2026-07...

opensource.posit.co

AI Newsletter: AGENTS.md vs Skills vs MCP servers

How to decide between the many ways of customizing agent behavior, plus Posit Assistant and package updates.

2111

Simon P. Couch @simonpcouch.com · 29/06/2026

We've made a bunch of changes in Posit Assistant with approval fatigue in mind: * Many obviously-safe commands will be automatically approved by the system. * /auto will have another model approve/reject any commands that would otherwise require your attention. assistant.posit.co/docs/feature...

0293

Reposted by Simon P. Couch

CascadiaRConference @cascadiarconf.bsky.social · 27/06/2026

Just wrapped up our first session, "AI, LLMs, and Big Data in R" with Kristin Bott, Ed Borasky, and Kylie Bemis"! We learned about using LLMs for coding in R,ethods for code parallelization, Posit and R tools for memory efficiency, and more. #LLMs #CascadiaRConf #AI #Posit #rstats #R #coding

0192

Simon P. Couch @simonpcouch.com · 26/06/2026

Interested in learning how to contribute to open source? We'd love to have you. :)

040

Reposted by Simon P. Couch

Emi Tanaka @emitanaka.org · 17/06/2026

Congratulations to the R Core Team! 🎉🎉🎉

0191

Reposted by Simon P. Couch

Julia Silge @juliasilge.com · 16/06/2026

I want to publicly thank @jcheng5.bsky.social for being willing to write this post, laying out how our AI tooling has evolved (including those eyebrow-raising product names)! 😅 opensource.posit.co/blog/2026-06...

opensource.posit.co

A brief and biased history of Posit data science agents

What we learned from Positron Assistant and Databot

14714

Simon P. Couch @simonpcouch.com · 15/06/2026

@sara-altman.bsky.social and I will be speaking at the R/Pharma GenAI Day tomorrow about agents for data science! The talk is free, virtual, and should also feel relevant for data folks outside of Pharma. :) Register: events.zoom.us/ev/AkKYQ7Ury...

An opening slide with title "It’s (still) very bad to be wrong: Agents for correct, transparent, and reproducible data analysis." To the right of the title is a series of AI-related R package hex stickers.

1152