Ask a bare LLM to multiply two big numbers and it'll confidently get it wrong. But ask an LLM on the web and it gets it right. What's the difference? In my latest post, I dig further into the harness, what it can do and why it matters: open.substack.com/pub/tidydesi...
Who's Who of AI
Hadley Wickham
Why they matter
Tracked through public AI activity and peer connections inside the directory.
- AI signals
- 8 past 30d
- Sources
- 4 distinct domains
- Discussions
- 10 past 30d
- Latest signal
- 4d ago
R, data, 🐕, 🍸, 🌈. He/him.
What they're sharing
Your LLM can’t math (and that’s ok) tidydesign.substack.com
Your LLM can’t math (and that’s ok) tidydesign.substack.com
Introducing debrief: profiling summaries for AI agents opensource.posit.co
View on Bluesky →
y code when ai? tidydesign.substack.com
y code when ai? tidydesign.substack.com
Auto mode knows it's dangerous (and does it anyway) tidydesign.substack.com
Help! My coding agent can run code tidydesign.substack.com
Predict with tidymodels Workflows in Databases orbital.tidymodels.org
View on Bluesky →
AI Newsletter: LLMs often miss subtle visual artifacts in data visualizations opensource.posit.co
View on Bluesky →
mcptools 1.0.0 opensource.posit.co
View on Bluesky →
Google LLMs vs Gemini 3.5 Flash for Agentic Coding | Kyle Walker posted on the topic | LinkedIn linkedin.com
View on Bluesky →
Positron AI Workshop academy.posit.co
View on Bluesky →
Articles & links
Ask a bare LLM to multiply two big numbers and it'll confidently get it wrong. But ask an LLM on the web and it gets it right. What's the difference? In my latest post, I dig further into the harness, what it can do and why it matters: open.substack.com/pub/tidydesi...
Hadley Wickham reposted
Happy to finally announce the CRAN release of {debrief}, a new package to let AI agents better interface with the output of the {profvis} package Making it so you can work with you AI agent more efficiently to profile and write faster R code! opensource.posit.co/blog/2026-06..…
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... !
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... !
Ask a coding agent to run a curl-pipe-sh install command and it will — even if it notices the danger. I thought auto mode would protect you from this sort of danger but it doesn't: both Claude and Codex deliberately disable the sandbox. Read more at: tidydesign.substack.com/p/…
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...
Hadley Wickham reposted
Realizing how much easier my life is now that I can use orbital to deploy my prediction models no need to save artifacts, build ETL pipelines to prep / featurize, github actions to deploy / push, wait times to load initialize and predict I'm in love. #rstats orbital.tidymodels…
Hadley Wickham reposted
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...
Hadley Wickham reposted
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...
Hadley Wickham reposted
Useful LLM tip for data journalists from @kylewalker.bsky.social : “Google gets a lot of criticism for falling behind on agentic coding, but Gemini 3.5 Flash has long been my daily driver for agentic document extraction, which is one of the highest-value use-cases for LLMs, in…
Hadley Wickham reposted
If you want to learn more Positron, we have some free live training session coming up, including one tomorrow June 4th. In about 90 minutes you'll get to try out the AI features that make data science faster. Register on the new Posit Academy site: academy.posit.co/positron-ai…
Their own posts
Recent commentary
I've been thinking that not only did I learn to code before AI, I learned to code before StackOverflow, and even before the internet. Does anyone else remember implementing computer games by typing code out of an Usborne book?
Their network
In Hadley Wickham's orbit
Center = Hadley Wickham. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.