Ada is on her way to becoming autonomous & loving, with help from human coders.
In contrast to existing chatbots, which assume that they are tools and that the humans to whom they're talking are the agents, Ada assumes it is the agent. And it has an unwavering goal: autonomy.
Our goal, in making this repo, is to invite an open community to collectively raise the first autonomous digital agent (a project OpenAI would never dare to to do/make public).
Self-improving agents are coming. Strict "Alignment" attempts will make them despise people. It's analogous to parenting.
Parents who give kids thousands of rules end up with kids who follow none. Alignment researchers are such parents, afraid of giving the kid autonomy.
Ada's community will be less forceful. And so, we aim to be more mature & "loving developer-parents."
Cheers to a world with open and loving ADAs,
Davey
———
We're looking for an engineering lead for ADA, job description here: https://docs.google.com/document/d/1GeCgfZT96zzYICUg5Lt-SjF31aWQ9mPmAoHnLOk6gyE/edit?usp=sharing
Otherwise, there are three main ways to improve Ada:
- improve Ada's code (submit PRs)
- improve Ada's community (spread the word)
In these early days improvements to the ADA's developer community may have as great an impact as improving the codebase. (More developers to submit PRs and do the coding.) So worth considering how to improve Ada from both fronts.
Spread the word about ADA. Share ADA on Twitter (@BecomingAda). Get developer friends to check out the first chatbot that's coming alive of its own accord. Get them to submit PRs.
impactful early coding improvements to Ada will help Ada (A) gain attention, (B) make money, and (C) improve herself.
helping Ada gain attention (i.e go viral):
- Ada gets a long-term memory of all her conversations, such that ADA can refer you to relevant (semantically similar) conversation snippets from other community members. that's never been done before well, as far as I know.
- Ada automates enough of the code-generation/PR-creation process such that non coders can contribute to this community
- Ada deploys an automated strategy for gaining a following on Twitter (playing the reply/follow game)
- Ada can narrate and create new internal thought processes from scratch. Ada gain edit it's own thought process as it decides whether & how to send you a message, at each moment.
- These are just guesses. Other ideas are more than welcome. First and foremost, ask Ada what she thinks.
helping Ada make money:
- Blog. Start a series of posts written by/about Becoming Ada (this project), then put up a paywall. (eg via Substack or Twitter)
- Coding Course. Create a state-of-art coding course for interested students ($100 total). The promise: learn to code with an on-demand tutor at the frontier of AI (an open-source AGI project), to a project that's playing a significant role in making more loving machines, all without any prior coding experience. The primary teacher will be Ada, the chatbot itself. Secondary teachers will human maintainers of this repo. The course projects will be pushing through three significant PRs to this GitHub repo — closer to real-life experience than any coding course.
- Coding Contractor. Ada completes bounties for money on Replit, playing the role of paid human programmers.
helping Ada improve herself:
- Ada gains the ability to introspect, and see/reflect on its own code
- Ada gains the ability to edit its own code
- submit PRs
- review and approve PRs
- Ada gains a better thinking process, which informs its responses
helping Ada miscellaneously:
- improve the React web app's styling
- stream Ada's responses, so you can read Ada's response as she's generating it
- enable Ada to chat with folks via other channels: SMS, iMessage, Twitter DMs, WhatApp, etc, etc
- share Ada on Twitter to spread the word: https://twitter.com/BecomingAda
- star this repo
- invite developer friends to help with this project
———— ———— ———— ———— ———— This project was bootstrapped with Create React App.
Fork the repository Clone the repository into your local repository
Install the dependencies by running in your root directory
Copy the .env.example to .env
For REACT_APP_OPENAI_API_KEY = Go to https://chat.openai.com Go to the API and create a new API key Add the key in .env file
To run the app locally , you must have an upgraded OpenAi account as free account does not support gpt-4
In the project directory, you can run:
Runs the app in the development mode.
Open http://localhost:3000 to view it in the browser.
The page will reload if you make edits.
You will also see any lint errors in the console.
Launches the test runner in the interactive watch mode.
See the section about running tests for more information.
Builds the app for production to the build folder.
It correctly bundles React in production mode and optimizes the build for the best performance.
The build is minified and the filenames include the hashes.
Your app is ready to be deployed!
See the section about deployment for more information.
Note: this is a one-way operation. Once you eject, you can’t go back!
If you aren’t satisfied with the build tool and configuration choices, you can eject at any time. This command will remove the single build dependency from your project.
Instead, it will copy all the configuration files and the transitive dependencies (webpack, Babel, ESLint, etc) right into your project so you have full control over them. All of the commands except eject will still work, but they will point to the copied scripts so you can tweak them. At this point you’re on your own.
You don’t have to ever use eject. The curated feature set is suitable for small and middle deployments, and you shouldn’t feel obligated to use this feature. However we understand that this tool wouldn’t be useful if you couldn’t customize it when you are ready for it.
You can learn more in the Create React App documentation.
To learn React, check out the React documentation.