artagnon.com

There was a recent announcement from Anthropic about using a team of agents to formalize Fermat's Last Theorem, and the generated artifact is over ten million lines of Lean code.

We argue that the sum total of everything LLMs do is a form of mutation or fuzzing, and that exactly one hard benchmark will suffice: number of tokens expended to converge to the mathematically correct output.

Humans have divisive tendencies, whether it's one human against another, one tribe against another, one race against another, one religion against another, or one country against another.

Starting from early childhood, I've constantly been made to feel inadequate.

I arrived in London fifteen years ago from a very poor farming village in Eritrea on a refugee status.

People who have good outcomes in life have a tendency to explain their choices in language around personal merit.

There are innumerable reasons to hate AI, starting with its environmental impact: the AI boom has been estimated to consume as much power as New York City, and as much water as the global consumption of bottled water in 2025.

As the year draws to a close, it helps to look back and reflect on some key changes in LLVM.

In a follow-up to the introductory article on auto-vectorization, we discuss how the loop vectorizer works internally.

Capitalism works by getting a small number of skilled humans to produce something or offer some service that can then be marketed and sold to a vast consumer class.

Any modern compiler has three main components: a front-end that parses the source language, and translates it to a middle-end intermediate representation, a middle-end that operates on this IR, performing target-independent optimizations with a bit of tar…

Most modern general purpose CPUs have a vector processing unit (VPU).

I'm eighty today, but the sequence of events I'm going to narrate took place when I was in my early twenties.

I woke up feeling like I had a brand new body and mind.

My heart started racing the moment I saw her.

I couldn't sleep that night.

A picture of artwork.

We investigate the limitations of statistical methods, a subclass of which is called "machine learning", taking the opportunity to touch on several aspects of the industry, including the future of employment, various industry practices, and privacy.

We illustrate how different programming languages influnced each other, and include a quick FAQ write up.

"I'm sorry, but we have to let you go", she says.

Today, we write a quick specialized note on what impredicativity exactly means, for those reasonably familiar with the Rocq syntax.

Here, we talk about equalities, and provide illustrative examples in vanilla Rocq, SProp, and HoTT.

Starting from the question of what consequence Gödel's incompleteness theorem has on the foundations of mathematics, we argue for new foundations, and build some intuition for these new foundations in Coq.

Using a mélange of mathematical syntaxes, we mechanize some exercises from Tao's excellent book Overture Let us informally define sets and set membership $\in$.

Both Lean and Rocq are proof assistants based on pCIC.

An input program function is represented using a Control Flow Graph (CFG).

Detecting loops in a directed graph can be tricky, depending on how you define your loop.

We are going to be discussing LLVM's Fast Register Allocator: you might like to open RegAllocFast.cpp and refer to it as we go through the article.

Our custom max function returns the maximum of two positive integers, and returns the negative integer, given a positive and negative integer.