# KVTop > Open research on memory and thought in machines: attention as recall by content, the KV state as a thought in progress, and the physics of the silicon underneath. Source: https://kvtop.ai/ (this file is the same page as plain markdown; updated 2026-11-14). # Open question: what is the unit of intelligence, and what does it cost? Shannon gave us the bit; Landauer, the least heat it takes to erase one. Neither measures understanding. What would — and what does it cost in joules and bytes? stage: early measurementsThe full question ## Posts latest - The first notes are in preparation. Each will carry its figures, its configuration and its raw data. Attention, live. Sixteen-dimensional keys seen as a turning two-dimensional shadow. The query recalls by similarity; the weighted mix of values is the thought it continues from; each step writes a new key. querykeysvalue compress Learning is compression. A trained model is the world folded into weights, kept only as far as it helps predict what comes next. read Thinking is reading. A query asks the memory a question, and recall happens by content, not by address. write Remembering is writing. Every token leaves a key and a value behind, so the next thought can find it. §1 ## Weights remember. The KV state thinks. A language model holds two kinds of memory, and they mirror a pair in the brain. We offer this as an analogy for intuition, not a claim about neuroscience. weights ### Long-term memory Like synaptic strengths, shaped slowly by learning. What the model knows about the world. written once, by training shared by every conversation while thinking read, never changed softmax( q · K⊤ / √d ) · V Attention is a soft lookup. The query is compared with every stored key, and the answer is a weighted mix of their values. It is recall by content, close to what neuroscience calls content-addressable memory. KV state ### The thought in progress Like the pattern of neural activity holding what you are thinking about right now. What the model has read, and what it is in the middle of saying. written one key and value per token, per layer belongs to one line of thought if lost forgotten, then rebuilt from the words §2 ## The chip is a door into high-dimensional space We live in three dimensions. A thought in a model lives in thousands. The chip is how we step through. cos θ(x, y) ≈ 𝒩(0, 1/d) In high dimensions, two random directions are almost always nearly orthogonal; the cosine between them shrinks like 1/√d. So a space of a few thousand dimensions has room for an enormous number of keys that barely interfere. That is the geometry that makes recall by content possible, and silicon is the only place we can walk around in it. Exact density of cos θ for uniform random directions, (1 − x²)(d−3)/2, each curve scaled to the same peak height. §3 ## Open questions These are the questions we work toward. None is answered here. Each one is stated so that an experiment could prove us wrong. ### How much of a thought must be remembered? A conversation's KV state grows with every token. Which part of it carries the information the next token needs, and what is the smallest state that leaves the output unchanged? stage: question ### What does a thought cost, in joules and bytes? Generating a token means reading the weights and the KV state through a finite channel. Where is the physical floor for one step of thinking on real silicon, and how close can a machine come to it? stage: first measurements taken ### Does a faster thought leave room for more thinkers? Speculating several tokens ahead makes one stream quicker but holds more memory for longer. When many lines of thought share one machine, does the gain survive? stage: research note in preparation ### How do two minds agree on a key? When a thought moves between machines that divide the work differently, they must name the same memory the same way. What is the right notion of identity for a piece of thought? stage: question §4 ## About ### The question we work on How can we define and measure intelligence in mathematical and physical terms — and understand its cost in joules and bytes? Shannon’s bit measures uncertainty; Landauer’s principle bounds the heat of erasing one, under stated conditions. Neither measures understanding. We want to know how prediction, compression and memory make up intelligent behaviour, and which of the energy, storage and data movement we pay for it are necessary, and which belong to the way we have built it. stage: early hardware measurements; theoretical connections under investigation KVTop publishes open ideas; the first code and data are being prepared for release. Mechanisms and methods will be public, with their limits stated. We work by four rules: Measure before believing. Start from what the hardware and the data actually do, then form the idea. Say how we know. Every number carries its evidence: reproduced, measured, or inferred. Publish what failed. Negative results and abandoned paths go on the record beside the ones that worked. Keep it small. One idea, one piece of code, one set of data that anyone can read in an afternoon. The most valuable thing you can send us is a reproduction, a counterexample, or a better question. Find us at github.com/KVTop-AI. Look up. For most of history the night sky was the largest space a person could see. The spaces inside a model are larger, and the chip is a telescope pointed at them. We build it carefully, measure it honestly, and share what we see.