The Future of Programming (and Why I'm Building a New Language)
Quentin Feuillade--Montixi · April 15, 2026
Today I'm open sourcing Weft, a programming language for AI systems. LLMs, humans, infrastructure, and APIs as base ingredients, a compiler that checks the architecture, and an AI builder that writes it in a fraction of the tokens other tools waste.
Three Properties for Alignment (and Why We're Not Training Them)
Quentin Feuillade--Montixi · March 16, 2026
Alignment means nothing without specifying what you're aligned to. I propose three concrete, mechanistic properties: Red Lines, Embodiment, and Resilience; and sketch a training procedure that could get us there.
The Topology of LLM Behavior
Quentin Feuillade--Montixi · February 27, 2026
A mental model for prompt engineering: think of LLM generation as a weighted random walk through a semantic space shaped by attractors. Two distinct operations follow from this: navigating around attractors, and reshaping the topology itself.