Assistant has separate project option and global options, so you can turn next edit suggestions off for specific projects. :)
05.03.2026 22:26
👍 3
🔁 0
💬 0
📌 0
Assistant has separate project option and global options, so you can turn next edit suggestions off for specific projects. :)
A digital CAPTCHA verification window titled "Select all squares with PIPES" against a plain white background. The window contains a 3×3 grid of numbered squares, mixing literal hardware, smoking pipes, and programming syntax.
These captchas just keep getting harder #rstats
Fares very well. :)
The description mirrored by input, which used "lat/lon." Looks like it just silently corrected me lol
Yeah, CLIs in RStudio isn't a very pleasant experience. Especially Gemini CLI😅
Posit AI is a $20/mo subscription. With the subscription, the experience is managed by the IDE, so no API keys involved.
Here's a page with more details on that question: docs.posit.co/posit-ai/use...
Not a dumb question. :)
We have a zero data retention agreement with our model providers. Users can choose to opt-in to data storage on Posit's side to help us improve the service, but users are opted-out by default.
A screenshot of an RStudio window. On the left-hand side is a new pain called Posit Assistant. The Posit Assistant had recently run code making a lat-lon plot of Washington state, colored by whether the point had been marked as forested or not.
Today we're releasing AI for RStudio. It's really, really good—I'd encourage you to point it at the messiest data sources you have and see what it can do.
www.simonpcouch.com/blog/2026-03...
Published some notes on the situation at Qwen - they released the Qwen 3.5 family (an outstanding family of open weight models) but now their lead researcher and several others all appear to have resigned within the past 24 hours simonwillison.net/2026/Mar/4/q...
Oh, shit
A pink and blue graphic reading "apply for our opportunity scholarship to posit::conf(2026)."
We are covering 40 people's travel, lodging, and registration for posit::conf() this fall! If you are from a group that is underrepresented in data science or open source, please consider applying for the Opportunity Scholarship—we'd love to have you join.
posit.co/blog/apply-t...
If you live in Chicago and you want to check your voter registration and see a copy of your sample ballot, the Board of Elections has you covered.
A code editor containing R code with a panel on the right showing a comment from 'Tidy reviewer'. On the left, the workspace setup section loads various libraries including tidyverse, extraDistr, MASS, cmdstanr, and bayesplot. Three lines (tidyr, purrr, and ggplot2) are highlighted in red, indicating they've been flagged. The 'Tidy Reviewer' panel displays feedback explaining that these three packages are redundant because tidyverse already includes them, suggesting their removal to simplify dependencies.
In this @posit.co AI Newsletter, GGML joins hugging face, and some reflections on a Docs-style interface to LLM code review in #rstats.
posit.co/blog/2026-02...
Very, very excited to be keynoting at posit::conf() with @sara-altman.bsky.social. Dream come true.
Anthropic: "Statement from Dario Amodei on our discussions with the Department of War"
www.anthropic.com/news/stateme...
I'm thrilled to be a fellow at the #NICAR26 data journalism conference this year!
I'll also be coaching a hands-on session on #RStats data analysis + plotting using #tidyverse packages. 📊
Maybe I'll see you there! 👇🏽
schedules.ire.org/nicar-2026/#...
#ddj @ire.org
this this this this this
There's promise in using LLMs for code review, but it's tricky things to make sure it's not overwhelming.
I was looking at this new experimental package by Simon Couch and I really love how it allows you to review code iteratively. #rstats #ai #llms
github.com/simonpcouch/...
Thank you! :)
Folks from underrepresented groups in data science and open source: we'd love to have you join!
this thread is blowing my mind
omg I literally have this in my .Rprofile because I cannot stand the data.frame print method:
print.data.frame <- function(x) {
library(tibble)
cat("# Just a data frame.\n")
print(structure(x, class = c("tbl_df", "tbl", "data.frame")))
}
"the function does not work"
hahaha I promise you I'm not checking for completeness from my side...
Been neat to learn about projects that I feel like I otherwise may not have come across there!
I appreciate you sharing—learning a lot from this.
Want to check if code using #GenAI generates the responses you want? Here's how to automate LLM evals with the {vitals} #RStats 📦 by @simonpcouch.com @posit.co
My latest at #InfoWorld:
www.infoworld.com/article/4130...
#LLMs
I'm very grateful that Luis maintains this guide. Very much recommend to those who haven't poked around there before! #rstats
I’m happy to announce Rapp v0.3.0 — a package that makes it easy to build and share polished CLI applications written in R.
Read more: www.tidyverse.org/blog/2026/02...
A bar chart showing the electricity use of several daily activities with the subtitle "The 'typical query' is not a useful way to think about coding agents' energy use." The bar for a 'typical ChatGPT query' is not even visible. My median Claude Code session is somewhere between the average US household per minute and toasting bread for three minutes. My median day with Claude Code is something like running a dishwasher.
I've recently been wondering whether the "median query" is still the right level of observation to speak about electricity usage of AI. Increasingly popular interfaces like coding agents and research/web search are much more compute-intensive.
www.simonpcouch.com/blog/2026-01...
@sara-altman.bsky.social and I’s latest newsletter includes a somewhat atypical call to action: if it’s been more than ~4 months since you’ve tried a coding agent, I’d urge you to try Claude Code or Codex with today’s models. The models and harnesses have progressed a lot.
posit.co/blog/2026-02...