Deterministic AI research

Every output can be re-derived by hand.

Aleten builds Ackren, a deterministic conversational engine for regulated deployment. No statistical inference anywhere in the pipeline, single-digit millisecond responses, and a derivation log for every answer. Ackren is pre-product: the development log is public, the specifications go out as each one is finished, and the engine is live to try while the product demo is four to six months away.

Latency · measured
~7,700×
Response
3.6 ms
Artefact · Octavo
16 MB
SRAM · plus mapped index
50 KB

A binder's back mark. A correct gathering shows an unbroken diagonal, and a wrong one visibly breaks. Six hundred years old, no instrument required, read by eye in a second. Hover or tap the mark to put it out of sequence.

Development log

What changed, and in which build

Every entry in full, monthly minimum. If the cadence is missed, this page says so rather than going quiet. Corrections are a first-class entry type and superseded figures are struck, never deleted.

Showing all 9 entries

Research28 Jul 2026

The formal specification is finished at v0.4

It goes out as it stands, with no form in front of it and no email address collected. The maths is the strongest asset here, so it is the first thing to leave the building.

Spec v0.4

Build24 Jul 2026

Trigram hit rate raised to 0.461 on the held-out set

Up from 0.449. Pruning still removes 55.1% of trigram mass, so a 16 MB build remains a bigram model with trigram exceptions.

Build 7f2a9c31

Correction18 Jul 2026

Majority voting withdrawn from the annotation regime

It only works if errors are independent, and on ambiguous items they are not. Replaced with triple annotation and expert adjudication.

Regime v2

Regulatory11 Jul 2026

The AI Act dates after the Digital Omnibus

Annex III high-risk deferred to 2 December 2027. Article 50 transparency stays on 2 August 2026, and it applies to us. Determinism buys nothing there.

Reviewed 11 Jul 2026

Build3 Jul 2026

Derivation log schema settled, versioned and open

The record format fixed before anyone asked for it, under a permissive licence, with a changelog and an invitation to implement it.

Schema v1.0.0

Research26 Jun 2026

Silent lookup errors, counted rather than estimated

Roughly 6,100 in a billion queries at the current index width. They are bought off with bits, and the bits cost most of a 16 MB budget.

Spec v0.4 §7

Programme19 Jun 2026

The verification programme, and what it pays

Four hundred hours at fifteen pounds, paid per verified hour rather than per item, so the incentive is not to rush the unsure cases.

Programme v1

Build5 Jun 2026

Octavo fits in 16 MB, with a weaker guarantee

One false accept in 4,096, against one in 16.7 million on Quarto. Twelve-bit fingerprints are all the budget allows, and that is said with the name.

Build 4c81e0a2

Correction29 May 2026

The energy comparison has been withdrawn

It rested on a batch size nobody has published, so it was not a figure we could defend. Struck until it can be recomputed. Latency is unaffected.

2 to 6 ×10⁵ · withdrawn, not replaced

Claims v1.1

Build22 May 2026

Mean fanout measured at 2.60

One to three reads per lookup, which is what makes a memory-mapped artefact viable.

Build 9d1c40b7

Research15 May 2026

Speech act layers one and two land in the core

They come with the engine as a mathematical consequence, not as a product decision.

Spec v0.3

Regulatory8 May 2026

IEC 62304 gap analysis, first pass

Deterministic software has a certification path. Most of the gap is documentation we have not written.

Reviewed 8 May 2026

Correction24 Apr 2026

The SRAM figure was quoted without its qualifier

"Runs in 50 KB" does not survive one technical reader. The full form is now the only form.

Claims v1.0

Build17 Apr 2026

The repair path was built before the response path

A system that is honest before it is capable can be made capable. The other order rarely recovers.

Build 2b7fd014

Programme3 Apr 2026

Contract terms published before hiring anyone

IP assignment and confidentiality shown before the first batch, not after it.

Programme v0.9

Research20 Mar 2026

Thirty-six thousand qualia relations, and what they miss

The count is the easy part. Coverage is the number that decides whether the engine can answer you.

KB v0.6

Build6 Mar 2026

First end-to-end turn on Quarto hardware

One question, one answer, one derivation record, on a board with an SD card and no operating system.

Build 5e9a1c33

Research20 Feb 2026

The repair surface replaces the answer

Not a banner above it, not an amber underline. When something is flagged there is no answer to decorate.

Spec v0.2

The full development log

Ackren

Three formats, one engine

All formats and packs

The names are printer's sheet folds: folio is one fold, quarto two, octavo three. Format names the hardware floor, not the competence, and any pack runs on any format subject only to flash. This is not a capability ladder.

Run it yourself

The engine is live at ackren.com

It grounds what you tell it, asks its own follow-up questions, and prints the derivation log for every turn, including the typed flag on the turns it refuses. It knows nothing yet and says so rather than guess. The playground needs no account and the conversation never leaves your browser.

Research

Publish the mathematics

Every document is dated, versioned and citable, and every figure carries the basis it was derived from: measured, computed, modelled or cited. A number without its basis is not a claim, and it does not appear on this site.

  • Grammar and parsing
  • Qualia relations
  • Determinism
  • Verification
  • Derivation logging
  • Regulated deployment

These are not posted yet, so this is a list rather than a set of links. Each one goes up at a stable URL as it is finished, with nothing behind a form. Ask for any of them now and you will get the current version: research@aleten.com.

All research

Work with us

We are hiring, and the terms are published

The verification programme pays fifteen pounds an hour, per verified hour rather than per item, so the incentive is not to rush the unsure cases. The quality regime is public before you apply: five per cent seeded gold items, twenty per cent triple annotated, and Fleiss' kappa reported.

No application form and no tracking system. Every role above has its own page with the terms on it. Write to work@aleten.com saying which one you want and a person will reply.