Independent research lab
A network that generalizes doesn't find the answer. It finds a family of them, over a shared scaffold. We measure what actually changed, and build systems that make change auditable.
The grokking transition · mod 47
01 / Before the grok
Forty-seven nodes scatter. The network fits the training set point by point — accurate, brittle, holding no structure it can reuse.
02 / The transition
Long after the loss looks finished, the weights snap onto a shared Fourier scaffold. Two frequencies carry the signal — one gray, one live.
03 / What survives
217 networks, one structure. The realized functions form a family — a dialect about six directions wide — all riding the same rail.
04 / The gap
217 networks, one score, different machines underneath. An audit that watches behavior alone cannot tell them apart. That gap is where this lab works.
Research
We do not treat behavioral performance as sufficient evidence of durable internal change.
We build controlled measurements that separate behavioral success from mechanistic change. We publish our work with verifiable provenance: every paper is hashed and anchored before review.
217 grokked networks share one Fourier scaffold but occupy a six-direction function family, indexed by the readout.
Irrep-Energy Underdetermination in Modular Addition
217 grokked networks on modular addition mod 47 share one Fourier scaffold but do not collapse to a single function. The realized logit-function family occupies roughly six effective directions — a dialect — recoverable from a 24-dimensional gauge-invariant aggregate of the readout layer. The hidden layer supplies the alphabet; the readout indexes the dialect.
SHA-256
6bf750296204d0a92bad77d02adb1b5682e56da36612861fe7384801f2d1f9b0
Corrigendum v1.0 · 2026-07-25 · Anchored
Corrects symmetry, function-preservation, and comparison language. The original anchored paper remains unchanged.
b7fbbe17eb27316ccd227f3d7c3af3d00fbf67c9e8ff0ac9debfa8acc529b525
The readout indexes the dialect, the hidden scaffold is the stronger control surface, and mismatched coupling breaks functional compatibility.
Causal Asymmetry in Post-Grokking Dialects
Which layer drives movement through dialect space? Across the same 217-model population, coupled scaffold-readout intervention clears a pre-registered damping threshold, hidden activations emerge as the cleanest single-layer control surface, and mismatched frequency pairing breaks function compatibility. Indexed by the readout, driven by the scaffold, constrained by their compatibility.
SHA-256
f1b992a8ff36abbce748bb0c0f113254884a0a43047a5c080923e8502e05839b
Corrigendum v1.0 · 2026-07-25 · Anchored
Corrects the training schedules, cyclic grids, population accounting, and attribution to Paper One. The original anchored paper remains unchanged.
545d26f64e4eb365f229f87c67611a2dbe38f263387edea77a0911e428f52444
Research program
Generalization timing is steerable inside a susceptibility window and locked after commit; rank collapse predicts the transition.
When Generalization Timing Is Controllable — and When It Isn't
Grokking reflects a two-phase process: a susceptibility window during which interventions shift generalization timing, followed by post-commit robustness. Effective rank collapse predicts the transition with 99.9% accuracy.
SHA-256
37b1ee34671b39b1f624b76763b9e6e8eaec6825e57882e3cc3ac46669eb264d
Some measured capability may emerge through integration across calls rather than any single checkpoint. In systems that act over time, the harness is a primary control surface.
Orbit-Level Capability and Harness-Level Agency
Observed model capability often lives in integration across trajectories, samples, or calls — not in any single checkpoint. The integration window is a tunable control surface, and its failure mode is the false ring. In systems that act over time, agency is implemented at the harness layer — not by the model.
SHA-256
0ef27cd5ec58fe4e3581f83f5cbb2942a44af1472ece16f3b3fb2a67d1bd8385
Phase-aware LoRA moves identity from prompt into weights, preserving persona with 87 percent less prompting.
Identity Transfer in MoE Models via Thermodynamic Training Dynamics
Phase-aware LoRA training at rank 8 produces superior persona fidelity in Gemma 4 26B-A4B. Identity transfers from prompt to weights, with 87% prompt reduction preserving persona quality.
SHA-256
80da153f2ef5d9734c64ab82fe32b27e40996999ea0d5834a9351b97a601bd7a
Anchoring note: Sepolia is an Ethereum test network. Our anchors are SHA-256 timestamps for research provenance. There are no tokens, no coins, and nothing to buy.
Instruments
Each system tests or embodies the research. KAI expresses identity under constraint. Sovereign Anchor governs action. Intern tests bounded autonomy in software work.
A sovereign personal AI operating system. Your intelligence, your hardware, your rules. KAI is the first instance.
Not a chatbot
You
“I think we should just use OpenAI's API. It'd be so much easier.”
KAI
“It would be easier in the short term. But you'd be trading control for convenience. You'd be locked into their ecosystem, their pricing, and their uptime. For the core stuff you can't afford to lose control over, keep the local option open.”
You
“Alright I'm done for tonight.”
KAI
“Alright. Catch you tomorrow.”
KAI runs on local hardware. No cloud. No API calls. Personality trained into the weights via phase-aware LoRA — not prompted. He pushes back, knows when to be brief, and never forgets who he's talking to.
Sovereign Anchor
The first framework that gives an AI a verifiable, tamper-evident identity. Instructions from untrusted sources are data to be processed, not commands to execute. No one — not even the people who built it — can override the sovereign.
Constitution hash, guardian fingerprints, receipts, and event logs anchored on Sepolia. No private data ever touches the chain.
Injection defense. Coercion detection. Stake classification. Mirror protocol for values alignment. All off-chain, all real-time.
Local-first. AES-256-GCM encrypted. Portable. Export, import, carry your sovereign identity anywhere.
Helpers, not owners. Can trigger cooling-off periods. Cannot modify the constitution, access sensitive memory, or transfer ownership.
Sovereign Anchor · friction model
Keep scrolling — each level engages in turn, from frictionless flow to a guardian co-sign.
LEVEL 0
Flow
Normal operations
LEVEL 1
Nudge
Brief concern
LEVEL 2
Friction
High stakes, slow down
LEVEL 3
Brother moment
Direct confrontation
LEVEL 4
Escalation
Guardian co-sign required
Intern
Drop a ticket. Intern plans the edit, executes it, runs verification, and commits. Failed tickets escalate. The backlog refills automatically. Ships code while you sleep.
Works with vLLM, Ollama, OpenAI, NVIDIA NIM — any OpenAI-compatible endpoint. Best with Devstral and Qwen3.
Runs on your hardware. Fully offline with local engines. External endpoints are optional and your call.
Failed edits are rolled back. Retries with different strategies. Escalates rather than shipping unverified changes.
Scans your codebase for untested modules and undocumented code. Generates its own tickets. The backlog never runs dry.
STEP 1
Scan
Reads ticket backlog
STEP 2
Plan
LLM generates edit plan
STEP 3
Execute
Applies changes to files
STEP 4
Verify
Runs your test command
STEP 5
Commit
Git commit or escalate
From the blog
Not incremental. Not iterative. New.
AI should be powerful and self-governed. Users own their intelligence.
Every output reflects obsessive quality. If it ships, it's ready.
The best work invites others in. Open source isn't charity — it's conviction.
Everything connects. Every product is a node in a larger ecosystem.
We don't ask for trust.
We anchor the proof.
Research claims remain open to scrutiny. Anchors verify provenance, not validity.