Jon Minton

Since its release on Thursday, I’ve been putting Opus 4.6 through its paces. No specific research task, evidence synthesis or review, or even philosophical conversation seems to challenge it, not even remotely.

So instead, I’m vibe coding a game!

jonminton.github.io/boomer/

Jon Minton’s Blog - How I Now Write My Blog With reMarkable and Claude Code

How I now write my blog (with reMarkable and Claude):

jonminton.github.io/jon-blog/pos...

Very meta. Hopefully specific and detailed enough to show this is a workable pattern for producing online content.

#claude #vscode #Remarkable #writing #cats

The Dilbert Future in retrospect

jonminton.github.io/jon-blog/posts…

#dilbert #ScottAdams #predictions

I asked an Agentic AI to develop a course on how to understand and use Agentic AI. This is what it came up with:

jonminton.github.io/working-with...

It has a core section, then five parallel tracks for different kinds of knowledge worker.

Suggestions and feedback very welcome!

📄 New paper out in Journal of the Royal Society of Medicine with @robaldridge.bsky.social, Rachel Burns, and analysis led by @jonminton.bsky.social

❓How does mortality compare by country/region of birth in England & Wales, 2007–2021?

doi.org/10.1177/0141...

🧵⬇️

Jon Minton’s Blog - David Sconce and the benevolence of evil? Some discomforting thoughts on The Mortician

New AI cowriting experiment. Are my blog posts better if I don’t write them?!
jonminton.github.io/jon-blog/pos...

I’ve done a cliche! Here’s a Gemini produced infographic of my end of year blog post:

jonminton.github.io/jon-blog/pos...

New blog post. A reflection on 2025, and why it might be the last year we think “nothing’s changed”:

jonminton.github.io/jon-blog/pos...

I thought this was about whale oil!

New experimental stats website (Alpha stage). Interactive tutorials for helping understand GLMs:

jonminton.github.io/glm-dashboar...

Please explore and make use of the bug and feature request options!

New blog post:
Claude Sonnet 4.5 reflects on reading and fact-checking the rest of my blog! (About 200k words!)

jonminton.github.io/jon-blog/pos...

Jon Minton’s Blog - WiredClothMother

New blog post: WiredClothMother

jonminton.github.io/jon-blog/pos...

I wrote an essay comparing AI to the Maxim gun of the 19th century, then asked four LLMs to produce short ‘rights of reply’:

jonminton.github.io/jon-blog/pos...

Given recent announcements of tougher asylum policies in the UK, I asked Claude AI to track down and summarise evidence on how much of an influence policy is likely to have on asylum claims as compared with other factors:

claude.ai/share/188b49...

(tl;dr: probably not much)

I’m now being overly sycophantic to Claude by suggesting its single letter substitution is actually a really clever shorthand for describing Vince Gilligan’s new TV show #pluribus

As a stats in-joke I thought redesigning the “Breaking Bad” titles to say “Breaking Blind” would be fun, so I asked Claude to have a go at this. It helpfully pointed out that “Bl” isn’t a real element, but decided that “Bk” must be good enough as it’s just 1 letter away.

As a stats in-joke I thought redesigning the “Breaking Bad” titles to say “Breaking Blind” would be, so I asked Claude to have a go at this. It helpfully pointed out that “Bl” isn’t a real element, but decided that “Bk” must be good enough as it’s just 1 letter away.

As a stats in-joke I thought redesigning the “Breaking Bad” titles to say “Breaking Blind” would be, so I asked Claude to have a go at this. It helpfully pointed out that “Bl” isn’t a real element, but decided that “Bk” must be good enough as it’s just 1 letter away.

Good comparison. Except in the Jasmine arc only the most traumatised cynic (Conor) supported the plan, whereas in Pluribus only one (maybe two) of the dozen or so people with free will/autonomy seems to think it’s a bad idea.

Jon Minton’s Blog - Point estimates, Confidence Intervals and P-Values Two simple statistical animations co-produced with Claude

Two animated guides for understanding some key concepts in statistical inference:

jonminton.github.io/jon-blog/pos...

(Or at least for becoming curious enough about these concepts to want to learn more…)

If it’s like Among Us, Werewolf, etc, I’m guessing almost everyone is little better than chance in their guesses - because lying and lie-detecting were stuck in an evolutionary arms race for millions of years - but comes up with a lot of reasonable sounding explanations for their decisions?

pkgdown 2.2.0 The latest version of pkgdown automatically builds markdown files that make it easy for LLMs to use your website.

pkgdown 2.2.0 now out — tidyverse.org/blog/2025/11.... Main feature is new build_llm_docs() which makes your websites easier to understand by LLMs. (Which you can easily turn off if desired) #rstats

purrr 1.2.0 This release tightens up the package by removing long-deprecated functions, making `map_chr()` and predicate functions more type-safe, and requiring a newer version of carrier to make `in_parallel()`...

purrr 1.2.0 out now — mostly removing long deprecated functions but a few small performance nad parallel processing improvements. Learn more at www.tidyverse.org/blog/2025/11... #rstats

Someone on ‘the other place’ just unearthed and reposted this data vis I made a couple of years ago. Such is the decline in engagement- there or here- that even 8 likes now looks impressive!

New blog post: Claude as a dialectical engine?

jonminton.github.io/jon-blog/pos...

(Have LLMs now solved their sycophancy problem?)

Long stolen antiques roadshow: set in the British Museum?

D’oh!

I’ve now experienced an LLM (Claude) start to ask me questions and push back on specific suggestions and assumptions I’ve made either implicitly or explicitly through the prompt. To me this suggests LLMs are moving from ‘Affirmation Engines’ to ‘Dialectical Engines’, a change I wasn’t expecting.

✨ Proofread translations ✨ by hadley · Pull Request #2926 · r-lib/pkgdown with Claude code cc @jayhesselberth @maelle

Would any fluent speakers of Korean or Chinese have a couple of minutes to review some updated pkgdown translations at github.com/r-lib/pkgdow... ? These were generated by claude code, so they're probably ok, but I'd love a human to double check.

Climbing with Claude: understanding git/GitHub for collaborative version control:

jonminton.github.io/jon-blog/pos...