6 New AI Projects Based on LLMs and OpenAI

4.6/5 - (7 votes)

I have just released another blog post with some of the most popular generative AI projects:

💡 Recommended: From Crafting Dog Portraits to Exposing Twitter Bots — 8 Unbelievable AI Innovations Shaking Up the World Today! 🐶🐦💡

The projects in this article I found after publishing the article but they are so exciting that I thought I’ll share them too.

Let’s get started! 👇

Project 1- PromptPerfect: Make Prompts Better with LLMs

Making good prompts can be hard – a great prompt helps create amazing AI-made content. 🤖 But don’t worry, PromptPerfect is here to help!

This handy tool makes prompt-making easier by automatically fixing your prompts for ChatGPT, GPT-3.5, DALL-E 2, StableDiffusion, and MidJourney. 🛠️

If you’re a prompt creator, writer, or AI builder, PromptPerfect makes fixing prompts simple and easy. With a user-friendly design and strong features, PromptPerfect brings out the best in LLMs and LMs, giving you great results every time. 🌟

Say bye to bad AI-created content and hello to perfect prompts with PromptPerfect! 👋

👉 Link: https://promptperfect.jina.ai/

Project 2 – BabyAGI GitHub

This Python code is a simple version of an AI-run task manager. It uses OpenAI and Chroma to make, sort, and do tasks. The main thought is that it makes tasks from earlier tasks and a set goal.

The code then uses OpenAI’s language skills to make new tasks based on the goal, and Chroma to keep and find task results for understanding. This is a simpler form of the first Task-Driven Autonomous Agent.

👉 Check out GitHub

Project 3 – Camel

Fast progress in chat-based language models helps solve hard tasks. But, they need people to help guide the chat, which can be hard and slow. 🐢

This paper looks at making it easier for chat helpers to work together and understand their thinking. 💡 They suggest a new chat helper plan called role-playing using special prompts to help chat agents finish tasks while staying in line with what people want. 🎭

They show how role-playing can make chat data to study how chat agents work and what they can do. This is helpful for learning about chat language models. 👩‍🔬

Their work brings a new chat helper plan, a helpful way to learn about how chat helpers work together, and shares our tools for others to use. 🌟

👉 Learn More

Project 4 – Grade School Math

Top language models can do many things as well as people, but they still have a hard time with step-by-step math thinking. 🧮 To find out why they fail and help research, this repository shares GSM8K, a set of 8.5K well-made and different grade school math word problems. 📚

OpenAI Blog Post

Even the biggest models don’t do well on these tests, even though the problems seem simple. 😕

This project tries to fix this!

👉 Learn More

Project 5 – AI Tutor

An AI tutor is a type of educational technology that uses artificial intelligence algorithms and machine learning techniques to provide customized and personalized learning experiences to students.

It can assess a student’s comprehension level, identify their strengths and weaknesses, and provide appropriate feedback and guidance in real-time. AI tutors can be implemented in various educational settings, including K-12 schools, universities, and online courses.

This tool focuses on teaching Python as an example.

👉 Learn More

Project 6 – AutoGPT in Your Browser

This runs the famous AutoGPT in the browser – but you must log in and you must provide your OpenAI API key.

👉 Recommended: What is AutoGPT and How to Get Started?

👉 Learn More


If you haven’t already, definitely download our free OpenAI cheat sheet teaching you the Python commands to use OpenAI in your own projects as a programmer:

💡 Recommended: Python OpenAI API Cheat Sheet (Free)

If you’re not a coder but a prompter, check out our prompting cheat sheet too!