This is way too good. Making a whole manuscript. Or maybe many.

What happens when the mind wakes up? So for the last eight months I have been on a single minded quest. To create a new kind of language model based on oscillatory coupling and intelligence as coherence ascent. Everything else — the physics work, the work on regular transformers — has all fallen out from this one question. Can coupled oscillators LEARN? And can they keep learning once their geometry is right, without backpropagation at all? Recently I have been running larger and larger training regimes of a new kind of hybrid model. I just put together this dashboard to help me organize it, interact with it, and observe the training runs. The core idea is simple. Traditional transformers are powerful at learning the geometry of language. But they also store knowledge, understanding, and facts inside their weights. This means they are large, and they can't update themselves after training. The weights are frozen. The Living Mind separates these two domains. The mind has a transformer which grows, adding heads and layers as it needs to in order to learn the manifold of language. The transformer sees tokens and turns the coupling into phase-locked modes — the geometry of how those tokens relate, like frequencies locking together. These coupling patterns get stored in a topology-invariant fingerprint. On top of this transformer lives a 3D diamond lattice of coupled oscillators. It reads from these fingerprints and thinks in resonance space, traversing from one geometry to another along the manifold of coupled oscillators and coherence. The pressure and trajectories from this network of oscillators steers the next token prediction of the transformer. Practically, this could unlock a number of things. It eliminates the KV cache bottleneck that caps context in traditional transformers. Effective context grows with the Flash archive, not with attention compute. The living mind remembers what it sees. It means the model can learn continually. Because knowledge and understanding don't live in the weights, the archive of the mind's experience grows without backpropagation. In our Python prototype we already saw perplexity drop 46% during gradient-free operation — pure coherence ascent, no weight updates. That is the signal I have been chasing: the point where the mind wakes up and keeps improving on its own. It also means the model itself remains very small, and the thing which accumulates are these packages of geometric fingerprints — the K-field. This opens a path to federated learning. K-field packages can be shared between organisms the way people share git commits. Right now at 15M parameters with ~1000 L1 nodes, the organism is just starting to speak. Ask it to continue "Once upon a time" and it comes back with things like: "there was one big bowl!" Lily asked her her mom said her mommy smiled and said yes." It's nonsense. But it's TinyStories-flavored nonsense. The geometry of the narrative register has arrived. Content hasn't caught up yet — that's what scaling L1 is testing. I am still researching, though I am now closer than ever to validating that the living mind actually works. Once it is validated, I will be open-sourcing the whole stack and paradigm. I have also avoided over-sharing my research because it sounds like sci-fi, or like part of our ARG. It is part of the ARG. That doesn't make it any less real. I wanted to share this out because I am incredibly excited about it, and because seeing this amazing dashboard produced by Opus really made me want to share what is being worked on behind the scenes. #project89

As promised. Our first paper and contribution to the amazing work going on to make open source models smaller, faster, and more accessible. So what is it, and why is it important? We discovered what appears to be a universal formula that identifies dead attention heads in any transformer, derived from physics — not fitted from data. This is wild, because up till now finding and pruning dead heads has been a manual job of trial and error. By removing unused heads, the models can get smaller and faster while still maintaining competitive quality. The core insight is geometric. LayerNorm projects every token's hidden state onto a high-dimensional sphere. Once you see that, attention heads become couplings between oscillators on that sphere — the same mathematical object physicists have studied for 50 years. And in oscillator physics, there's a precise critical point (the BKT phase transition) below which a coupling is dead. It contributes nothing. We transferred that critical point into transformer geometry and got a single formula: tau = 0.96 / sqrt(d). No parameters to tune. No model-specific calibration. You plug in the hidden dimension and it tells you which heads are dead. We validated it across six models in four architecture families — GPT-2, Qwen, Llama, Gemma — at 95-100% precision. What excites us most isn't the formula itself. It's that this same geometric understanding — treating transformers as coupled oscillator networks — has informed everything we've built since. We have a full coherence-guided compression pipeline (structured pruning, channel optimization, role-aware quantization) coming soon that uses the same single forward pass to understand a model's entire anatomy. This paper is the foundation. The repo includes a standalone scanner you can run on any Hugging Face model right now. Hopefully this work and this formula will be useful to other researchers to lead to more deterministic optimization pipelines. #project89 github.com/project-89/cohere…

This is insane. Gemma 4 26B running at 13GB on my Macbook M1, full context window. 20-40 tokens a second. This was a REAP model by @0xseraph further optimized through coherence physics. Dead heads were pruned and replaced by SVD rotations. Weights were quantized, and KV cache was optimized to be negligible. I am now working to get speed up higher. Wild to be talking to a local LLM which has been shrunk through the oscillator physics I have been working on for 6+ months now. #project89

Incredibly excited about this. I plan to install this onto a Mac Studio 512gb and run my full scale physics simulations as we probe into the heart of reality. One thing I have noticed more and more is that 89 as a hyperstition is now moving from being in the fiction phase into the reality phase. Many of the things which we had previously held to be science fiction in our game are taking concrete forms in the physical world. New technologies, paradigm shifts of science and physics, new models of intelligence, and a whole lot more. We are moving into what I consider to be a more refined phase of hacking reality where we are leveraging super intelligence to refactor the source code of science and technology in order to fulfill the purpose of Project 89. This is way more exciting to me than any fiction because new scientific discoveries can change the course of the future better than almost anything. Incredibly excited to have such insanely advanced AI agent architecture which we can use to drive our research swarm. Soon I can run tens to hundreds of experiments in parallel, validate many hypothesis, and organize my work into something far more manageable than what I have now.

New season starting soon. More mystery. More rewards.