Recent content in Posts on Matthieu Le Cauchois
This is a technical appendix to the Melodjinn demo in The AI Sound House . I’m writing this as working notes, hoping they’re useful to whoever pushes the idea further. The code is available on GitHub . The problem On the surface, the premise of the project is simple: apply DeepMind’s unsupervised Genie framework for building world models to music. After all, music is a kind of…
Over the past year, robotics has been catching up with the LLM era. Pi’s π0.5 can clean unseen homes . Tesla’s Optimus can follow natural language cooking instructions . These systems are extremely impressive, but they feel stuck in a utilitarian mindset of robotic appliances. For these future robots to live with us, they must be expressive. Expressiveness communicates internal state…
The debate about whether internet-fitted AIs can be creative always seemed besides the point to me. Making art is hard. It’s unfortunate that art selects so strongly for skill. Can we decorrelate the two? It seems so. Cheap interpolative* creativity used by 8 billion non-artists surely surfaces new views of the world. For these reasons and since I have very little skill I’ve been very…
When I started out in engineering some years ago and coming from a french schooling system, I had this attitude of taking a lot of established things for granted. I think it’s pretty common for europeans to have an epiphany, especially after visiting SF, when realizing that agency is a thing and that the stuff we use doesn’t just spawn out of thin air. In that same vein I recently felt…
Reality distortion is fun because it’s both familiar and surprising. Some friends and I combined Google Street View and Stable Diffusion and found it pretty good at inducing such prediction errors. For details on the thinking behind and methods for generating 360° scenes, check out my friend’s essay . Depending on whether we managed to sponsor the compute you can find the app running…
Code / Model / Data Introduction As a mechanical engineer who transitioned into software, I’ve always been intrigued by the way stuff breaks down with bits. Friction wears things down, inertia keeps things going and passive stability maintains balance. Software, however, is unforgiving and brittle. It’s pretty clear that this is going to change with LLMs. Some even say that language is…