A Memory That Knows How Sure It Is
How beliefs work in agent memory: belief networks, calibrated decision models and self-organizing context, a design that learns which sources to trust, and the experiments I’d run to test it.
AI
Posts
What Agent Memory Is Missing
Agents remember plenty. They have no idea how much to believe it. What memory is, what cognitive psychology says about it, and why an assistant that remembers everything still gets your sister’s birthday wrong.
LeWorldModel vs V-JEPA: What Actually Changed
LeWorldModel removes masking, EMA, and stop-gradient from V-JEPA, trains end-to-end from pixels in hours on one GPU, and plans 48x faster. Here’s the full architecture and what it learns differently.
SIGReg: The Anti-Collapse Trick That Actually Has a Proof
V-JEPA prevents collapse with heuristics. SIGReg prevents it with a theorem. Here’s what isotropic Gaussian means, why variance isn’t enough, and how the Cramér-Wold trick makes it cheap.
V-JEPA Internals: Building My Understanding
Going back through V-JEPA’s encoder, predictor, and target encoder in detail — the mechanics of masking, EMA, stop-gradient, and why collapse prevention is harder than it looks.
What is a World Model? Clearing the Confusion
World models have become a buzzword in AI, but the concept is often misunderstood. Let me trace their history and give you a precise definition.
World Models for Robot Learning: Why Video Might Be All You Need
What if robots could learn just by watching? V-JEPA2 suggests that video understanding alone, combined with goal images, might be sufficient for robot manipulation.
World Models vs VLAs: Two Paths to Robot Intelligence
A detailed comparison of world model approaches (V-JEPA, DreamZero) and Vision-Language-Action models (Pi-Zero, OpenVLA) for robot learning.