Latest Posts (20 found)
Christian Jauvin 1 months ago

Intelligence and Computation

This article has been posted to my Substack also. There are two kinds of mathematics: “simple” ones, with which you can create a complex video game, implement a working replacement for a worldwide financial ecosystem (Bitcoin), or even raw intelligence, with neural networks. This math is simple in the sense that it is basic linear algebra (for video games and AI) and even simpler (but extremely convoluted) math, for Bitcoin. What makes this type of math powerful is that when you combine it with a computing substrate, you get very impressive and useful results. You can simulate reality, get conversational intelligence, etc.

ai AI programming Programming
0 views
Christian Jauvin 2 months ago

Au-delà du chatbot : un harnais pédagogique

Cet article a aussi été publié sur mon Substack . Dans le contexte de la révolution en cours dans le monde de l’IA, on peut parfois avoir l’impression que les néologismes apparaissent de manière trop rapide et désordonnée, et qu’il est difficile de suivre leur évolution. Le fait que ces néologismes apparaissent tout d’abord en anglais n’aide pas, car la plupart n’obtiennent jamais de traductions satisfaisantes ou officielles, et on est donc condamnés, en tant que francophones, à les utiliser tels quels dans nos phrases.

programming Programming
0 views
Christian Jauvin 2 months ago

Desiring, Thinking, Knowing, Doing

This article has been posted to my Substack also. Consider these situations: You want to write a novel Someone asks you what is the capital of Norway Someone asks you how you feel today Someone is telling you that their program has a bug Suppose that you would want to write a classic program (GOFAI-style), as an agent able to implement (perform) these four scenarios. How would it work? The first scenario should implement a kind of “desire state”. That desire state should have some “target”, which could be something like: a world in which a beautiful new novel exists, or simply, a desire to produce an interesting sequence of words, by itself. You want to write a novel Someone asks you what is the capital of Norway Someone asks you how you feel today Someone is telling you that their program has a bug

programming Programming ai AI
0 views
Christian Jauvin 4 months ago

The Windowsification of the Work Culture

When I was studying as a CS undergrad in 1998 at the University of Montreal, every student had a Linux account with a special folder in their where you could put stuff which would be instantly served on the web. It took me a while to see the beauty of it, because at that time, I didn’t know much about the web and Linux. Fast-forward in 2026, and I now work as a professor at an online university, and it’s strangely difficult to host anything online in that environment. Actually, it’s next to impossible. The only thing I have is an extremely slow and clunky web app to edit my home page. And whenever I change something using it, I’m always scared that I’m going to break or delete something. The only mechanism that is available for publishing stuff is based on Moodle, but it’s meant for the courses, and it’s not particularly user-friendly. So me and my (very few) colleagues, who want to publish stuff online in a more flexible way, are forced to use external platforms. But of course the University sees that with suspicious eyes. To someone who doesn’t know about it, Github might appear like a potentially “dangerous” platform. Who knows? Code is scary, because hackers are scary!

culture Culture
0 views
Christian Jauvin 6 months ago

What does it mean to create with AI?

For some weird reason, I always had some kind of slight “mental hesitation” with the meaning of data encoding versus decoding . Which one goes in what direction? To be honest, I have the same kind of weirdness with other concepts: daylight saving time for instance (are we gaining or losing an hour? I can never tell, sometimes even for many days after a change). So I wanted to create a diagram to illustrate the dichotomy between encoding and decoding, for a course I’m creating on software engineering. So one way to “create with AI” would be to ask one: “Can you please create a diagram to illustrate the difference between data encoding and decoding”.

design Design ai AI
0 views
Christian Jauvin 7 months ago

The reverse difficulty of translation

Most often when we think about the difficulties associated with the translation of a language, we are thinking in one direction: you are learning a new language, and it is difficult to translate your own language and thoughts into this new one. This difficulty feels extremely real and visceral, and engages generally with many aspects of your overall cognitive experience: it’s difficult to remember words, grammar rules, it’s embarrassing to make mistakes, frustrating to not feel understood, etc.

writing Writing
0 views
Christian Jauvin 7 months ago

Est-ce que ChatGPT sait ce qu'est une question?

J’expliquais récemment à un ami que ChatGPT, dans son essence, n’est « qu’un » modèle de prédiction du mot suivant, celui qui vient après une suite d’autres mots. Ainsi, quand on lui demande « Quelle est la capitale de la France ? », il ne répond pas (vraiment) à la question : il complète plutôt une séquence de mots sur laquelle il a été entraîné, en profondeur et avec une très grande efficacité.

nlp Nlp programming Programming ai AI
0 views
Christian Jauvin 7 months ago

Does ChatGPT know what is a question?

I was explaining to a friend recently that ChatGPT, to its core, is “just” a model to predict the next word, the one coming after a bunch of other words. So when you ask it “What is the capital of France?”, it does not (really) answer your question, it completes a sequence of words on which it has been trained, deeply and efficiently. So considering that, it might seem that ChatGPT is in a situation that would be akin to you, if someone tells you a bunch of words you don’t understand (in a foreign language say) and then, someone else gives you a card, on which you can find some words to pronounce, as a reply (in a language that you don’t understand but can read, let’s say).

nlp Nlp ai AI
0 views
Christian Jauvin 9 months ago

Vibe coding a bridge between two VS Code extensions

With VS Code I am writing a lot of Markdown text these days (for instance this Hugo blog) and I’m using two extensions to help with my word processing needs: Code Spell Checker , which has a bunch of dictionaries for many languages (I use French). Auto Correct , which is much more obscure extension (its code has not been updated for many years), which allows to automatically change a word to another one, as I write, based on a list of entries managed in . Code Spell Checker , which has a bunch of dictionaries for many languages (I use French).

programming Programming
0 views
Christian Jauvin 10 months ago

Voting as a way to surface the hidden reasons

Imagine a situation where the majority holds a kind of quiet veto over change. Not because the status quo truly serves them, but because, taken one person at a time, it feels easier to keep things as they are: less awkwardness, less risk, less responsibility. So an arrangement persists that benefits no one in the aggregate, yet survives because it is individually convenient to uphold. Now picture someone who wants to change this, but who feels—socially, institutionally, psychologically—almost powerless. One natural impulse is to appeal to democracy: hold a vote. Let the majority decide.

business Business
0 views
Christian Jauvin 10 months ago

Insurmountable Hans

The ARC benchmark was designed by François Chollet to serve one goal : be sufficiently difficult, demanding so that it cannot be “hacked” by some “cheating” AI techniques, LLM or whatever. But it must do so in a rigorous, systematic and simple to define way, it cannot be vague or ambiguous. It must be (relatively) easy for a human, but hard for a program. And when I first looked at it, I admired its simplicity and purity: the problems are simple but deep, and it’s clear that for many of them, you need to grasp something that goes beyond mere pattern recognition or superficial pattern matching. They seem to require some seriously deeper thinking. And if, like me, you thought for a minute about how you’d try to tackle them, in a programmatic way (ML or otherwise), it was quite easy to become convinced, that this is quite a good benchmark. And at first, what happened, on Kaggle, for instance, was exactly that: nobody could get even remotely decent results, the problem set really felt like a though nut to crack. From there, the temptation was great, to suggest the idea that whenever ARC would be cracked, AGI would have arrived!

ai AI machine-learning Machine Learning
0 views
Christian Jauvin 10 months ago

Metaphysical Boldness

Digital physics is the body of mathematical and philosophical work treating the universe and the way it works as a giant digital computer. This is often associated with cellular automata, and names like Konrad Zuse, John Von Neumann, Stephen Wolfram, etc. What I find fascinating about this field is that the models it suggests are making very deep metaphysical claims: if they are true, it means that the underlying structure of the world is much different than we think, and radically simpler in a sense. Take the lattice gas automaton for instance. A version of it is an hexagonal cellular automata with very simple collision rules, not more complicated than the famous Rule 30 or 110 , for 1D cellular automata. The impressive thing about it is that a simulation running this rule with many particles can be shown to approximate the Navier-Stokes equations , which are the classical complicated mathematics to describe the dynamics of fluids. Following Wolfram, I find it very appealing to consider the idea that the world is not somehow running “hidden mathematics”, somewhere and somehow, to solve some complicated equations in a seemingly magical way, but rather, that things are radically simpler, in that the world is simply implementing a set of trivially simple rules. The world is not concerned with, or made with mathematics, mathematics just emerges, with inherent and irreducible complexity, from extreme simplicity.

programming Programming data Data Science
0 views
Christian Jauvin 10 months ago

Manifesto: AI (as a term and field) should subsume CS

In French the term “informatique” feels slightly better, as a label to describe the field, than “Computer Science” feels in English. But this is a rare occurrence for French, because most of the other terms, like “technologie de l’information”, and “science des données”, feel awkward and far from their “real” cultural counterpart, the thing in itself that we do, when we do it.

ai AI Science culture Culture
0 views
Christian Jauvin 10 months ago

We didn't get the AI failure modes that philosophy anticipated

The original idea of AI, that we got mostly through science-fiction, and also a little from the philosophy of mind and logic, imagined an entity that would implement idealized and mechanical notions of thoughts, reasoning and logic. Such an entity would of course know everything there is to know about such topics, and its behavior would thus be rooted in them. Although this would mean that the entity would generally behave in impressive and powerful ways, it was also implicitly understood that sometimes this “perfection” would lead to paradoxical behaviors and “errors”: the robot stuck in a circle in the Asimov story is the quintessential example.

Science ai AI
0 views
Christian Jauvin 11 months ago

Render a markdown table to docx with pandoc

Suppose you’re like me, in the middle of editing a Word document, and you realize that you’re fed up with Word. So you tell it to a colleague, who happily tells you: use pandoc , it can render docx files! So here you go, and you first try to convert this simple markdown: Then you run this command, with a lot of hope:

web-development Web Development tutorial Tutorial programming Programming
0 views
Christian Jauvin 12 months ago

Proof of Prompt

When I’m doing freelance software development projects and I’m asked how much time things will take, it’s always very hard to answer. It’s a very high dimensional problem, and you have many degrees of freedom: how much should you charge, should you do it per hour or not, if you use AI how should it be factored in the efforts and time you report, what is the separation between the stuff that you charge and the stuff for which you don’t charge, does asking questions to your client to better understand the problem, on Slack in the weekend, count as time or not? Faced with these doubts, I guess that most people are quite happy to fudge a rough number, do a couple of rounds of negotiation about it, reach an agreement, and call it a day. They implicitly accept that the outcome of this process can go both ways: either you estimated too low, and this way you will lose something, or the contrary. And you hope that in the grand scheme of things, things should average out in a reasonable way: either your loss, or their loss, who cares in the end? But is is really working this way?

career Career business Business
0 views
Christian Jauvin 1 years ago

Ignore Your Check Engine Light at Your Own Peril

Currently in my car I have the “check engine” light being on, but it’s ok, because I know what is the problem, my mechanic told me that it’s , and that even though it’s not ideal, it can wait while he finds the part to repair it (apparently it’s not so easy to find). There is something I don’t like about this though: if there is a NEW problem appearing, I won’t know about it, because this check engine light has only one state, and now it’s being used.

Electronics hardware Hardware
1 views
Christian Jauvin 1 years ago

Learning Persian with Anki, ChatGPT and YouTube

I’ve been learning Persian (Farsi) for a while now, and I’m using a bunch of tools for it. The central one is certainly Anki , a spaced repetition app to train memory. I’m creating my own never-ending deck of cards, with different types of content, for different purposes. The most frequent type of cards is grammar focused phrases (very rarely single words) coming sometimes from my own daily life, but also very often directly from videos of the Persian Learning YouTube channel, created by Majid, a very talented and nice Persian teacher, in my opinion.

tutorial Tutorial
1 views
Christian Jauvin 1 years ago

An Excel-like editable data grid widget with Streamlit

I recently spent a lot of time trying to come up with an interactive data grid widget in Streamlit . It needed to be a bit like Excel: the value you enter in a cell should trigger the recomputation of the value in another cell. At first I assumed it would be relatively easy, but given the powerful state management model at the heart of Streamlit, I found out that it wasn’t. State management for UI programming remains a hard problem, no matter what is the environment. The most difficult aspect of React programming, for instance, is certainly state management. The user-driven asynchronous nature of a UI makes it an inherently difficult problem.

python Python javascript JavaScript
0 views
Christian Jauvin 1 years ago

What if AI Had Come First?

Imagine an alternate history in which AI, in the sense of our current LLMs, had come first. This possibly means that things would have looked much more like they did in the 2001: A Space Odyssey movie: computers having a user interface so powerful that you don’t really need anything else (apart from a set of fancy looking dashboards maybe). But this is not what we got. First we got something that looked quite a bit like an idealized “command box” (not vocal though, but textual), with which you could give instructions to the computer, almost as if you were talking to it. But not quite. These instructions had to be expressed in a “language” that the computer could understand, and of course it was far from human natural language. Very close to that command box was the notion of a written program that you could give to the machine, and which would be executed as a kind of chain of commands, in long form, with more elaborate logic and syntax.

ai AI
0 views