Miklós Koren
banner
koren.mk
Miklós Koren
@koren.mk

Professor at ceu.edu. Data Editor at Restud.com.

Economics 76%
Business 11%
Pinned
How to make sure you ran reproduce all steps of your research months later? We demoed our CLI tool bead.zip that saves code and data together at RSECon at Warwick. Slides bead.zip/rsecon25

My rainbow window sticker approves of the music. Prepping for KGLW concert tomorrow.

Now it just keeps apologizing.

I could imagine a thought process of "no large RDBMS needed" but, I mean, it has "SQL" in the name.

I had an AI agent refer to SQLite as "noSQL-like DB."

Looks like it was trained on Medium/LinkedIn bullshit but I told it in no uncertain terms that this does not pass with me.

Today I was playing with econometrics (matrices and stuff) as well as relational data modelling (how are different entities related) and realized something.

> Econometrics is data modelling without the data.

I made a similar point in a talk some years ago (github.com/korenmiklos/...)
github.com

This morning I heard my son hum Nirvana in the bathroom. Not sure if I should be proud or worried.

Claude Sonnet 4.5 is currently working on the script that will get me what I want.

Users don't need chatbots. They need to seamlessly integrate AI into their workflows to minimize their pain. If Google doesn't understand this, they are in trouble.

I subscribed to Google Gemini and cancelled it within 5 minutes.

I wanted to create a Google Form from a survey instrument in Google Doc. Gemini cannot do that. It suggested to go to Google Forms and create one myself, using the Doc as a guide.

Super stoked about Krasznahorkai's Nobel Prize. A beautiful interview with him from a couple years ago: www.guardian.co.uk/books/2012/a...
László Krasznahorkai interview: 'This society is the result of 10,000 years?'
The Hungarian writer behind the formally experimental Satantango talks punctuation, inspiration and money-motivation to Richard Lea
www.guardian.co.uk

This. Today my coauthors complained that Github does not properly render the math from my @obsidian.md notes. By the time we finished the meeting, Claude Sonnet 4 has built a nifty CLI tool “ghmd” that converts Obsidian markdown to github flavor. Complete with unit tests and pipx installable.

When you start your commit message with bigfux: instead of bugfix: you can be sure it was a major bug.

The way AI helps human-to-human communications is underrated.

I used to be picky about collaborating on technical projects. Like, "don't send me an email, send me a pull request."

Now I do some of my best work just talking to coauthors. AI transcribes, AI summarizes using the project context.

My daughter taught me about www.doesthedogdie.com
DoesTheDogDie.com
Crowdsourced trigger warnings spoilers for movies, tv, books and more.
www.doesthedogdie.com

I have been working with coding AI agents several hours a day in the past couple of months. You get to know their style.

Grok is like Elon Musk. Moving fast and breaking things at 10x speed. Not apologizing either.

For the narrow subset of #econsky people clinging to their Stata and crunching big datasets with @duckdb.org, I have vibe coded a DuckDB extension that reads .dta files.

koren.dev/software/

Give it a spin and report issues! (Thanks, @anthropic.com Claude Code and the Python Pandas implementation.)

Always excited to hear Elhanan Helpman. If you're in Vienna, come by.

events.ceu.edu/2025-05-07/p...
Public Lecture: Elhanan Helpman
events.ceu.edu

Mac.

Why I love OneDrive, part 78.

My local folder is called

/Users/koren/OneDrive\ -\ Central\ European\ University\ \(CEU\ GmbH\ Hungarian\ Branch\ Office\)/

Luckily, I can symlink.

Good point, this never occurred to me.

Austrian Airlines is pitching Budapest for me.

I mean, I love the city. But as long as this is how well AI understands us, I feel safe.

I see a lot of scripts where the file name encodes some structure. Like analysis_this.do, analysis_that.do and plot_this.do, plot_that.do

If you have such a clear structure, you are best served by folders. It just as easy to write "src/analysis/whatever.do" as "src/analysis_whatever.do".

Ceci n’est pas une espresso machine.

Sorry, by internet I mean www. Was profoundly useless before proper search.

Not knowing what to ask is one of the best use cases of LLMs.

The technology is much better at deciphering what I want than SEO-infested web pages.
To me this seems similar to the early days of the internet. A promising technology with no product. Once the initial bubble bursts, we may yet see fantastic products leveraging the tech.
Newsletter: Generative AI is a marketing con perpetuated by Sam Altman and Dario Amodei through a mixture of lies and half-truths carried by a tech media that fails to ask the right questions. Outside of ChatGPT, generative AI companies barely get any traffic at all.

www.wheresyoured.at/longcon/
The Generative AI Con
It's been just over two years and two months since ChatGPT launched, and in that time we've seen Large Language Models (LLMs) blossom from a novel concept into one of the most craven cons of the 21st ...
www.wheresyoured.at

New level unlocked: typing an email, three letters into a word in the second sentence, get distracted, then go back and try to figure out what words begin with those three letters.

#adhdlife

Searching for Sugarman was such an awesome movie.

Why did we develop Kezdi.jl and what can you do with it?

Watch my presentation at JuliaCon in Eindhoven. #juliacon #juliasky #econsky

youtu.be/JklbLwgePis?...

docs.koren.dev/Kezdi.jl/dev/
Kezdi.jl: A data analysis package for economists | Koren | JuliaCon 2024
YouTube video by The Julia Programming Language
youtu.be

Image to text. English to German. Vague text to clean Python code. Legalese to human arguments.

Automating this translation seems both useful and profoundly risky for many white-collar jobs.