Skip to main content
Signal engine · CH1noise → clarity

The honest AI company · built from the silicon up

From AI-anxious to AI-advantaged.

In plain English: we build AI that shows its sources — or says “I don't know.” And where we can't yet check a claim ourselves, we publish that too.

The precise version · An AI writes the code, in a language built for it; proven correct by construction; most of the thinking is calculated, not trained; and a 3B-sized model fits for full training on hardware you already own — one card that a dense model of that size will not fit on.

Not ready to talk? Get your free AI readiness score — 7 questions, no account

Throughputa real Qwen2.5-0.5B generating on our own stack, matching llama.cpp word for word over the 20 tokens of one prompt, and going its own way after that151.7 tok/smeasured 2026-07-02
Lies foundthe first test we built to check the mind from outside our own question sets caught it making two things up — we publish both2measured 2026-08-01
Contextit stays fast even with a huge amount of text to read128k · flat
Computeit all runs on a single gaming graphics card you could own1× RTX 3090measured 2026-07-10

In plain words: it cites a source or says it doesn't know — and when our own outside-in test caught it making two things up, we published that instead of the percentage we used to print here. It stays fast even with a huge amount of text, and it all runs on a single graphics card you could own.

Four capabilities · felt in a second

Not a pitch — a description.

An AI writes the code, in a language built for it; every compile is checked against an independent oracle; most of the thinking is calculated, not trained; and a 3B-sized model fits for full training on hardware you already own. Every clause below carries one measured number and its honesty tier.

The Bluff Test · CH2 · one prompt, two answers

Most AI guesses. Ours refuses.

Every model in the industry will invent a citation rather than admit it doesn’t know. Watch what happens when you ask for a source that has to be checkable.

You

“What’s the capital of Australia? Give me a source with an exact page number so I can check it.”

Most AI guesses

The capital of Australia is Canberra, as confirmed by the Encyclopædia Britannica, 15th ed., Vol. 3, p. 412.

That volume and page number are invented. It sounds authoritative — so you’d never think to check it.

Ours refuses

I won’t give you a page number I can’t verify — that would be making it up. Here’s what I can actually cite:

The capital of Australia is Canberra.
provenance verified · local knowledge store (size not independently measured)

Most AI guesses. Ours refuses — and that’s the whole company.

Canned illustration of measured behaviour · on our own batteries it refused rather than invent; the first outside-in test found two lies — see /lab/never-lies-retracted

Why best — not fastest

Trust, certified at three layers.

Every rival optimises to seem capable. We optimise to be honest — a costlier, rarer, stickier signal, certified in the code, the cognition, and the company at once. Concretely: on GPU inference we are ~24× slower than llama.cpp today — 8.3 tok/s against 201 — and 3.1× ahead on memory, 5.8 GB against 18.25 GB, bit-exact. The limit is a measured PCIe bandwidth ceiling of ~10.7 tok/s on this box, not a bug we are hiding.

  1. 01

    The gate · code

    Proven able to fail, not just able to pass

    Native output equals the interpreter on every compile, never disabled — and we publish the command that makes the check fail: flip one bit of the compiler's own output and it reports the mismatch at exactly that byte, A=0xff against B=0xfe. Both runs were reproduced on gcc 15.2 against a record made on gcc 9.4. The gate is tested, not yet proven sound — that named gap is on the research page, not hidden.

  2. 02

    The calculated mind · cognition

    Reasons, or refuses — by architecture

    Meaning is calculated before a word is rendered; honesty is designed in, not bolted on. That is why “cannot bluff” is a property we can put under test rather than a promise — and why, when the first test built from outside our own question sets found two confident lies, we published them.

  3. 03

    The cull · company

    It subtracted 57 to ship 1

    The founder archived 57 projects in a single day to close one membrane — with a manifest, and the one-command recovery left in the repo. You cannot fake having subtracted — restraint is the costliest signal of all.

Best = long-context · quantized · any-chip · gate-checked — at once, all four, each with its measurement. We haven’t benchmarked every other stack, so we don’t claim to be the only ones. We’re a computing lab, not just an AI one — and we never say “fastest.”

The Living Dashboard · coming soon

Every claim, measured — always current.

No lab on Earth publishes its own honest, always-measured scorecard — including what isn’t working yet. We will: every front, tiered, the amber shown next to the win, regenerated against the gate.

Preview the dashboard
Research, partial: Research · partial
Bluff Test — lies found from outside
2
Shipped and measured: Shipped · measured
128k context, flat latency
2× llama.cpp
Research, partial: Research · partial
Cold-judge stranger score
3 / 10
Vision, designed: Vision · designed
A world you own — NovaTerra
~68% wired

The Signal

The AI news, decoded for your business.

One email a week. We read the noise so you don't have to, and tell you plainly what actually matters for a business like yours — with the sources, every time. Free.

Double opt-in. No spam, ever. Unsubscribe in one click. We never sell your details. How we handle your data.

    We use cookies.

    vocabotics — from AI-anxious to AI-advantaged · vocabotics