https://github.com/danielrosehill/iterative-llm-prompting-cycle

A repository describing a process for iteratively improving LLM prompt outputs
https://github.com/danielrosehill/iterative-llm-prompting-cycle

Last synced: 6 days ago
JSON representation

A repository describing a process for iteratively improving LLM prompt outputs

• Host: GitHub
• URL: https://github.com/danielrosehill/iterative-llm-prompting-cycle
• Owner: danielrosehill
• Created: 2024-07-24T17:06:46.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-07-24T17:59:14.000Z (4 months ago)
• Last Synced: 2024-11-12T23:18:13.703Z (6 days ago)
• Homepage:
• Size: 183 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# An Iterative Cycle For Improving GPT Outputs

The purpose of this repository is to describe an iterative cycle for improving the effectiveness of prompts to a generative pre-trained tranformer (GPT).

This workflow was developed for working with ChatGPT although it may also work with other LLMs.

The workflow described here is simple but it might nevertheless provided a good foundational workflow for those looking to explore the capabilities of GPTs beyond naive prompting. 

## Contents 

Summary

- `summary.md`

Workflow description

-  `workflow.md`

Prompt iteration example

- `/demo_prompt_iteration`

GPT configuration text

- `promptoptimisationgpt_config`

Schematics

-  `/schematics`

## Schematic

![Schematic](schematics/1/diagram.png)

## Authorship

By:

Daniel Rosehill

(public at danielrosehill dot com)