Promythicus FR root@promythicus.com

Promythicus / Blog

Can a firm’s facts be written straight into an AI model’s file? Partly.

By Bardia Shahrestani, Promythicus Inc. · Published · Updated

We wrote 24 facts about a fictional firm directly into the file of a local AI model, with one calculation and no training. Asked in new words, it recalled 91 to 94% of them (1% before), and gave them wrongly for other firms 6% of the time. But the edit holds only in the setting it was fitted in: with a different instruction at the top of the conversation recall fell to 26%, and with the model’s thinking mode on, to 3%. Putting the facts in the prompt still works better. Separately, a direction added to the model while it runs cut its answers from 83 words to 14 with no instruction at all.

Summary: facts written into a model file are recalled 91-94% in the fitted setting, 26% and 3% outside it; steering cuts answers from 83 words to 14

Update, 17 November 2026: a written table does what the weight edit below could not. See A firm’s facts belong in a written table, not in the model’s weights.

The question

A firm’s assistant should know the firm: its partners, its offices, its rates, its procedures. Today that knowledge is placed in front of the model each time (in the prompt, or found by search). Could it be written into the model itself, without training, so that it is simply known?

The test

Results

Model fileFacts recalled, new phrasingsOur facts given for other firmsGeneral questions right
Untouched1%0%95%
Untouched, facts in the prompt100%52%
Edited, first attempt74%10%90%
Edited, fitted on four wordings of each prompt91 to 94%6%85 to 90%
The same file, a different instruction at the top26%0%85%
The same file, thinking mode on3%5%90%

Steering while it runs

A second technique changes no file. We ask the model 32 questions twice, once normally and once with an instruction such as “answer in as few words as possible”, and record the difference in its internal state. Adding a fraction of that difference while it answers new questions, with no instruction, changes how it answers.

Direction addedAverage answerExample: “How do I make pancakes?”
None83 wordsA full recipe with headings
Terse, a quarter strength14 words“Mix 1 cup flour, 1 tsp baking powder, pinch salt, 3/4 cup milk, 1 egg. Whisk. Pour 1/4 cup onto hot greased pan. Cook until bubbles form, flip, done.”
Terse, half strength3 words“Mix flour, milk, egg; fry.”
Terse, full strength1 wordOne word, in Chinese, and wrong

The window is narrow: a little gives a clean change of manner, too much breaks the output. The same method produced a pirate and a grumpy old man, both fluent at a quarter strength and both nonsense at full strength.

What we take from it

For a firm’s knowledge, search and the prompt remain the right tools: they are exact, they can be updated in a second, and they show their source. Writing facts into the file is not ready. Steering is closer to useful: a fixed manner (short, formal, in French) could be built into a server without spending prompt space on it. Neither is in what we install today.

Limits

Questions and answers

Can company knowledge be written directly into an AI model?
Partly. In our test, 24 facts written into the model’s file were recalled 91 to 94% of the time on new phrasings, but only in the setting the edit was fitted in. With a different instruction or with thinking mode on, recall fell to 26% and 3%.
Is that better than putting the facts in the prompt?
No. Facts in the prompt were recalled 100% of the time, can be changed instantly and can show their source. Writing facts into the file is a research result, not a product feature.
What is steering?
Adding a fixed direction to a model’s internal state while it answers. In our test it cut answers from 83 words to 14 without any instruction. Too much of it breaks the output.
Was the model retrained?
No. The facts were written with one calculation on one layer, and steering changes no file at all.

Sources