Artagnon

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. At this point, one would question the utility of such an artifact: the issu

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. We certainly don't have heated arguments abou

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. When we're not fighting one another, we theorize about the world ar

Starting from early childhood, I've constantly been made to feel inadequate. Other children in my school would neglect me, and I would often try to seek attention through eccentric acts, as any child would - my personality today is a product of being trea

I arrived in London fifteen years ago from a very poor farming village in Eritrea on a refugee status. Growing up, we didn't have access to a regular supply of clean drinking water, and went hungry on many occasions. I didn't even get the chance to go to

People who have good outcomes in life have a tendency to explain their choices in language around personal merit. Conversely, people who have poor outcomes have a tendency to explain their situations in language around personal demerit. The positive langu

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. The reasons could also be per

As the year draws to a close, it helps to look back and reflect on some key changes in LLVM. The article is written from my perspective, summarizing work I landed, along with adjacent work, in chronological order. In September 2024, Nikita Popov proposed

In a follow-up to the introductory article on auto-vectorization , we discuss how the loop vectorizer works internally. Nearly all transforms in LLVM work by directly manipulating IR, using the results of various analyses on the IR, while the loop vectori