DocumentationArchitecture
FastAdaptation
A zoomed-in view of one operation in Piro’s stateful inference loop.
Architecture detail
FastAdaptation
Updates the active fast-weight state from observed text and next-token prediction before later chunks are processed.
fastState, observedChunk, prediction, runtimeWeights): target = observedChunk.nextToken loss = CrossEntropy(prediction, target) update = Gradient(loss, fastState) return fastState - runtimeWeights.fastLearningRate · update