GithubHelp home page GithubHelp logo

fjborquez / force-multiplier Goto Github PK

View Code? Open in Web Editor NEW

This project forked from lspahija/force-multiplier

0.0 0.0 0.0 16.84 MB

Use AI to edit your documents in real-time. Provide feedback and let the AI do all the work.

Home Page: https://force-multiplier-production.up.railway.app/

License: MIT License

Shell 1.59% JavaScript 0.75% Python 36.62% TypeScript 59.36% HTML 0.70% Dockerfile 0.98%

force-multiplier's Introduction

FM

Force Multiplier

Feedback is All You Need

Most workers today are tasked with producing some sort of artifact (e.g. code, legal contract, documentation, essay, etc.)

The process might look something like this:

  1. supervisor gives their subordinate worker a task to write a legal contract
  2. subordinate worker goes off and writes a draft of a legal contract, which might take days or weeks
  3. subordinate worker brings draft to supervisor for review
  4. supervisor provides feedback
  5. subordinate worker modifies legal contract, taking supervisor's feedback into account
  6. steps 3-5 repeat until supervisor is satisfied with the legal contract

The main bottleneck in the above process is the subordinate worker taking time to write and modify the contract. Luckily, modern LLMs are orders of magnitude faster than humans at doing precisely this.

Force Multiplier allows the user to iteratively provide feedback to GPT-4, which then modifies the artifact (the legal contract in the example above) until the user is satisfied with the result.

The goal of Force Multiplier is to multiply the user's productivity by enabling them to become a supervisor that leverages GPT-4 as a subordinate worker.

force-multiplier.mp4

Efficiency

Force Multiplier only modifies the portions of your artifact that require modification, given your feedback. The rest of the artifact remains unchanged. This allows for fast iteration because it's not necessary to wait for the LLM to regenerate the entire artifact after each piece of feedback is given.

Core Functionality

Force Multiplier allows you to input any block of text as your initial document (artifact). You can then provide your feedback on this document, in terms of specific changes or overall sentiment. Force Multiplier will take your feedback, interpret it, and automatically modify your document in accordance with the feedback you provided.

You can iteratively provide feedback and watch your document change before your eyes until you arrive at your desired end result.

Run it Locally

  1. Clone the repo
git clone [email protected]:lspahija/force-multiplier.git
  1. Change directory to AIUI
cd force-multiplier
  1. Build Docker image
docker build -t forcemultiplier .

or if on arm64 architecture (including Apple Silicon):

docker buildx build --platform linux/arm64 -t forcemultiplier .
  1. Create Docker container from image
docker run -d -e OPENAI_API_KEY=<YOUR_API_KEY> -p 8000:80 forcemultiplier
  1. Navigate to localhost:8000 in a modern browser

Demo

https://force-multiplier-production.up.railway.app/

force-multiplier's People

Contributors

lspahija avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.