@jhelvy.bsky.social - John Paul Helveston

22 Oct 2026 20:01 +0000

@pingfanhu.bsky.social and I built our own editor. I know, I know…does the world really need another one? But Emaki 絵巻 is the tool I’ve wanted since I started using Claude Code and Codex, so we just went ahead and built it 🙃. We’re calling it an "agentic development environment" (ADE) ...🧵

16 Oct 2026 17:51 +0000

Didn't even make it to one Scaramucci https://www.nytimes.com/2026/10/16/us/politics/katie-zacharia-fired-press-secretary.html

16 Oct 2026 14:23 +0000

My piece in The Conversation today: Americans want electric cars, they just can't find them. For the past ~6 months, many articles have pointed to low EV sales as a sign of low EV demand, even with sky high gas prices. In my article, I show evidence that this is a market misread. ...🧵

06 Oct 2026 16:37 +0000

Walked into this today, and all I can think about is penguins #rstats

29 Sep 2026 10:00 +0000

Rolling back fuel economy standards during the worst Middle East oil crisis since the last Middle East oil crisis that prompted Congress to create those standards in the first place is...a choice

24 Sep 2026 19:52 +0000

earmark can now run on GitHub. Set up a repo, then add articles by listing them in a sources.yml file. Making a commit kicks off an action that converts the articles into mp3s that are served on GitHub pages. Listen to your articles from any podcast app! https://earmark-dev.github.io/earmark/github/setup.html

16 Sep 2026 22:38 +0000

Sharing a great little 6-min video by a creative film maker and story teller. Looks like he just getting started on some really cool work. https://youtu.be/IXRVD7ZqncQ?si=LaBYqCmX2zML4R00

13 Sep 2026 15:22 +0000

On my way to posit::conf(2026)! Looking forward to sharing ideas about data, code, AI, & tools with a fun and ridiculously creative community. And if you'll also be there, come to my talk Tues afternoon to see how we used #quarto and AI agents to build the vehicletrends.us dashboard!

09 Sep 2026 11:09 +0000

Terence Tao on OpenAI's Navier-Stokes solution

03 Sep 2026 15:23 +0000

Journal editors can't find reviewers because we're overwhelmed. I checked my gmail, review requests have more than doubled since the pre-LLM days. This is also why you're seeing more AI-generated reviews - reviewers can't keep up and reach for the LLM to get the job done faster (not better).

27 Aug 2026 00:07 +0000

Super proud of Dr. @pingfanhu.bsky.social, who successfully defended his dissertation today! In addition to writing his full dissertation, he created a storybook version that is so well done - check it out! https://pingfan-hu.github.io/2026-phd-storybook/

24 Aug 2026 22:57 +0000

👂Got an article you wanna listen to? Try this tool! It extracts text from a URL or document, converts it to a narrated MP3, and posts it to your own podcast feed you can subscribe to on your phone. One line and you get a new "episode" on your phone: earmark publish jhelvy.github.io/earmark/ https://jhelvy.github.io/earmark/

19 Aug 2026 23:15 +0000

Your opportunity to comment on the proposed NSF Guidance on Financial Assistance ends next Monday, August 24. There are WAY fewer comments on this than the earlier proposed OMB government-wide regulation, but this rule codify's the SAME policies! Attached is my comment to NSF.

14 Aug 2026 19:43 +0000

Thanks to everyone who joined our workshop today on Agentic Workflows with Claude Code! In case you missed it, we just posted the recording on YouTube: youtu.be/kX1bzUHZWqc Happy Claude Coding! https://youtu.be/kX1bzUHZWqc

11 Aug 2026 19:12 +0000

🚨 We're running a free 2-hour remote workshop this Friday on agentic workflows with Claude Code 🤖 If you're curious about how to get started with agentic workflows, you'll probably find this helpful. All workshop materials (and link to register) are at https://pingfan-hu.github.io/2026-agentic-workshop/

25 Jul 2026 00:38 +0000

Refreshing to hear people calling the bullshit what it is in @science.org Full article https://www.science.org/content/blog-post/assault-science-funding-continues

18 Jul 2026 22:05 +0000

The public overwhelmingly rejects OMB's federal grant rule change. I used the GPT 4o mini LLM to classify the comments, showing 94% in opposition. Of the 5% supporting, ~84% are verbatim copies. This blog post summarizes the results (full analysis linked in post). https://www.jhelvy.com/blog/2026-07-16-omb-grant-rule-comments/

14 Jul 2026 14:37 +0000

There are 496,769 comments on the OMB rule that will devastate U.S. science. Thank you 🙏 Little doubt this administration will shove this rule through anyway, but these comments will matter. The fight to defend science is not over. Many more battles to come. https://www.regulations.gov/docket/OMB-2026-0034/comments

06 Jul 2026 19:50 +0000

In 48 hours with #Claude code, I built a C++ backend to my logitr #rstats 📦 to make mixed logit model estimation ⚡ fast. There's no excuse now for slow software now when tools like CC are available to do the performance engineering. A post on this build out: https://www.jhelvy.com/blog/2026-07-03-logitr-faster-with-claude-code/

30 Jun 2026 16:58 +0000

Dissenting on a birthright citizenship case should be disqualifying for SCOTUS. Not only is the language of the 14th amendment abundantly clear, we fought a civil war to enshrine it in our constitution. That amendment was a very, very costly amendment. Shame on Alito, Gorsuch, and Thomas.

30 Jun 2026 14:21 +0000

This is an excellent talk on the recent history of AI progress in solving increasingly challenging problems in science and the shockingly consistent outcome that just scaling the models more leads to continued performance improvements. https://youtu.be/Mw60FH5iflI?si=A4N1PTSb7mFnd8Zf

24 Jun 2026 10:18 +0000

If you've ever been curious about how to use claude code skills, check out @pingfanhu.bsky.social's recent post. He shows how to leverage skills to encapsulate complex workflows and achieve impressively consistent outputs from agents. https://pingfanhu.com/blog/2026-06-24-agentic-skills/

22 Jun 2026 11:04 +0000

Excellent reporting and analysis on America's deadly mega trucks and SUVs https://www.nytimes.com/interactive/2026/06/21/us/trucks-suv-pedestrian-crashes.html

18 Jun 2026 14:43 +0000

🚨 The U.S. scientific enterprise faces an existential threat few are talking about. A proposed OMB rule would reshape ALL federal research funding — NIH, NSF, DOE, DOD, every agency. What it does & how to push back 👇 defendfederalresearch.org 🧵... https://defendfederalresearch.org

06 Jun 2026 12:41 +0000

🚨 5 alarm fire territory 🚨 https://www.nytimes.com/2026/06/05/well/ada-conference-diabetes-trump.html https://www.nytimes.com/2026/06/05/well/ada-conference-diabetes-trump.html?smid=nytcore-android-share

04 Jun 2026 13:15 +0000

I cannot think of a better fitting president for the 二百五 bill

02 Jun 2026 15:44 +0000

The BUILD America 250 Act charges #EV owners $130/year to "pay their fair share" in road taxes. Hogwash. Average drivers pay ~$95/yr in federal gas tax. A 50 mpg hybrid pays just $42, yet no surcharge for them. It's almost like this has nothing to do with tax revenue and is just an EV penalty 🤔

27 May 2026 14:37 +0000

Esp for use with LLMs - I'm increasingly convinced #quarto is the ideal LLM output. Separating *content* from *format* is so, so useful. https://www.jhelvy.com/blog/2026-05-12-quarto-optimal-claude-output/ [contains quote post or other embedded content]

13 May 2026 20:22 +0000

#Quarto is much more than a publishing framework. When leveraged with agents with Claude code, it's a powerhouse tool for agentic workflows. In this blog post, I make a few quick arguments for why you should check out Quarto if you're working with agents. https://www.jhelvy.com/blog/2026-05-12-quarto-optimal-claude-output/

03 May 2026 01:09 +0000

A less extreme version is just to put speed governors on every car. You can put the cap at something like 85mph, but seriously beyond that there is truly no reason to be allowed to drive faster except like running from the cops [contains quote post or other embedded content]