Almost every system we use to find and organise information runs on similarity: given a query, return the most alike item. Similarity is genuinely useful but it’s only one way things connect and the field has built almost everything on it alone. Stairs don’t resemble a slip, yet one evokes the other; the smell of sunscreen returns a whole holiday. Those links exist because the things were experienced together, not because they’re alike. Eridos takes that signal — temporal co-occurrence — and builds memory around it: the structure of lived experience reflected in the geometry of an embedding space. Across text, biology and beyond, it recovers associations that similarity misses entirely. The work builds toward systems that understand the reality they occupy.
Eridos runs multiple, related lines of research: associative memory built from experience, computation in optical and crystalline substrates and exploration in multi oscillator reservoir computing. Different layers of the stack but the same instinct: question the assumption everyone else builds on.
Six papers: temporal co-occurrence as a learning signal across text and genomics, plus wave-optical storage of weight matrices in simulation.
A model trained on 10,000 novels discovers what text does rather than what it’s about. Explore the results interactively.
In simulation, packing many weight matrices into one shared wave-optical volume — where adding more can sharpen the patterns already stored rather than degrade them.