explaingit

sgup/ai

Analysis updated 2026-05-18

65Audience · developerComplexity · 1/5LicenseSetup · easy

TLDR

A small notes repo with a portable instruction set for AI coding assistants and a field test measuring whether those instructions change output.

Mindmap

mindmap
  root((sgup/ai))
    What it does
      Notes on AI coding agents
      Portable instruction set
      Behavioral field test
    Tech stack
      Markdown documents
    Use cases
      Standardize AI behavior
      Evaluate instruction impact
    Audience
      Developers using AI tools

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Apply a consistent set of behavioral guidelines to any AI coding assistant.

USE CASE 2

Read findings.md to see how much these instructions actually change an AI's output.

USE CASE 3

Use Fable5.md as a template for writing your own operating instructions for a model.

USE CASE 4

Compare no-instructions, old-instructions, and current-instructions behavior on a real codebase.

How does it compare?

sgup/ai5ec1cff/injectrcelvisun/loss-function-development
Stars656565
LanguageC++
Setup difficultyeasyhardeasy
Complexity1/54/53/5
Audiencedeveloperdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

This repository is a small collection of notes and configuration files for getting better results from AI coding assistants. It contains two documents, and the README describes them briefly without going into much technical detail. The first file, Fable5.md, is described as a portable set of instructions written to capture how the Fable 5 AI model approaches coding tasks: how it reasons, decides what to build, and communicates its output. The idea is that you can attach these instructions to any capable AI model to make it behave in a similar way, following principles like verifying before asserting, keeping changes small and reversible, leading with a recommendation when there are multiple options, grounding advice in the actual project rather than general theory, and being honest about the current state of things. The second file, findings.md, contains notes from a controlled test comparing three conditions: no instructions, an older version of the instructions, and the current version. The test was run on a real codebase to measure where these behavioral guidelines actually change an AI's output, where they have no effect, and whether the difference is worth the overhead of including them. The repository does not contain code. It is a reference document for people who work with AI coding tools and want to apply consistent behavioral guidelines across different models or projects. The README is sparse and points to the two markdown files for the substance. Licensed under MIT.

Copy-paste prompts

Prompt 1
Summarize the coding principles described in Fable5.md and how I could apply them to my own AI assistant setup.
Prompt 2
Explain what the A/B/C test in findings.md compared and what it concluded.
Prompt 3
Help me adapt Fable5.md's instructions for a different AI coding model.
Prompt 4
What did this test find about when behavioral instructions are worth the overhead?

Frequently asked questions

What is ai?

A small notes repo with a portable instruction set for AI coding assistants and a field test measuring whether those instructions change output.

What license does ai use?

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

How hard is ai to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is ai for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.