---
title: "Publication on Habr: when an LLM becomes predictable"
description: "A post about how prompts written as executable specifications make models more deterministic, turning them into an engineering tool for code generation."
date: 2025-08-19
display_date: "August 19, 2025"
image: "https://habrastorage.org/r/w1560/getpro/habr/upload_files/bf7/8d9/fb9/bf78d9fb95f5504ced77f9a7b9ceba4a.png"
image_alt: "When an LLM becomes predictable"
---

# Publication on Habr: when an LLM becomes predictable

<zoom-img
            src="https://habrastorage.org/r/w1560/getpro/habr/upload_files/bf7/8d9/fb9/bf78d9fb95f5504ced77f9a7b9ceba4a.png"
            alt="When an LLM becomes predictable"
            width="100px"
            style="float: left; margin: 15px 15px 0 0;"
    ></zoom-img>

A note titled **"When an LLM becomes predictable"** has been published. It examines the idea
        that when prompts are formulated as executable specifications, models begin to behave more deterministically.
        This opens the possibility of using them as an engineering tool for code generation, rather than just a
        "probabilistic interlocutor".

For **ADSM** this idea is especially important: formulating rules and specifications becomes the key
        to predictable agent work.

The note included a poll: *"Can an LLM be used as an engineering tool for generating code?"*

        73% responded "no, the model's probabilistic nature is too strong," 27% — "yes, a prompt can precisely
        describe the desired result".

Most people don't believe in the controllability of probabilistic models. I, however, am convinced they are
        deterministic enough for engineering solutions. Triggers in computer memory also spontaneously change state under
        hard radiation — and that problem is solvable. It's the same with models: the issue isn't that they are
        probabilistic, but how we work with their predictable zones.