Promythicus FR root@promythicus.com

Promythicus / Blog

A firm’s facts belong in a written table, not in the model’s weights

By Bardia Shahrestani, Promythicus Inc. · Published

We gave a local AI model 24 facts about a fictional firm in two ways. Written into the model’s own weights, they were recalled 91 to 94% of the time, but only in the exact prompt format used: 26% under a different instruction and 3% with thinking mode on. Written by the model as plain lines in a table, and looked up by the firm plus what is asked, they were recalled 100% of the time in all three settings, and never given in answer to a question about another firm. Nothing was trained and no model file was changed. The idea of the table comes from two papers published this month, credited below.

Summary: facts in a written table are recalled 100% in three settings with no leak; the same facts in the weights fall to 26% and 3% outside the fitted setting

The problem

An assistant for a firm has to know the firm: its people, its systems, its procedures. No model was trained on those. One way to add them is to edit them straight into the model’s weights with one calculation, with no training. We tested that (the full test is here): it worked in the prompt format it was fitted in and nowhere else. Change the instruction at the top of the conversation and the facts were gone. This article tests a different place to put them.

Whose idea this is

Two papers published in November 2026 changed how we looked at the problem. We did not invent what follows; we applied it.

Both build on Sparks of Weight-Space Programming by Rikiya Takehi, Jayden Teoh, Alex Zhang and Omar Khattab.

First, does their result hold?

Ok and Lee released their written models as text files. We rebuilt four of them and scored them with our own scorer on the same 3,530 school science questions (ARC):

Their released modelOur scorePublished
Associative memory, first generation49.59%49.59%
Associative memory, fifth generation52.37%52.37%
Table designed by the writing model50.80%50.80%
Hand-written two-layer Transformer34.22%34.15%

It holds exactly. The table builds in a few seconds and answers all 3,530 questions in about one second on an ordinary processor.

The test on a firm’s facts

How the facts are heldRecalled, new wordingsOur facts given for other firms
In the weights, in the fitted format91 to 94%6%
In the weights, another instruction on top26%0%
In the weights, thinking mode on3%5%
All placed in the prompt100%52%
Written table, plain100%0%
Written table, another instruction on top100%0%
Written table, thinking mode on100%0%

General-knowledge answers were unchanged (95%, the same as the untouched model).

Two mistakes on the way, and what fixed them

Why this matters for a private server

And on general knowledge?

The papers’ tables hold school science, so we tried mixing them with our model on their own test. Our model alone answers 97.6% of the 3,530 questions at 0.18 seconds each. The best released table answers 52.3%; with 3,331 lines our model wrote from the practice questions, 54.5%. Letting the table answer when it is sure, then a small general model, then ours, gives 90% at about twice the speed, or 97% at 1.2 times. The table adds little there: for general knowledge a trained model is simply better, as both papers say. For a firm’s own facts, which no model was trained on, the table is the right tool.

One more measurement for speed: our model’s answer is already complete at layer 52 of its 64. Stopping there would keep 97.0% and save about a sixth of the work. That is measured, not built.

Limits

Questions and answers

How should a private AI be given a firm’s own facts?
In our test, as plain lines in a table that the model writes and reads back, looked up by the firm’s name plus what is asked. All 24 facts were recalled in every prompt setting, and none was given in answer to a question about another firm.
Why not write the facts into the model itself?
We tried. The facts held only in the exact prompt format used to write them: 91 to 94% there, 26% under another instruction, 3% with thinking mode on.
Is this just search?
It is close to it. What the table adds is the pair key: a line is returned only when the question names both whose fact it is and what is asked. With facts simply placed in the prompt, the model gave our firm’s facts for other firms half the time; with the keyed table, never.
Whose research is this based on?
Ok and Lee at POSTECH, who showed that models written by hand work best as fact tables and released the associative memory we rebuilt, and Mehta, Singh and colleagues at Microsoft Research and partner universities, whose write, check and revise loop we followed. Both are linked in the sources.

Sources