📖 Summarizing Books with GPT-3.5

Disclaimer

This project demostration is for educational purpose only.

💡 About

This is an ongoing project inspired by OpenAI's demonstration on Summarizing books with human feedback.

🧠 Rationale

Lifes are too short for worth reading books

I have a long list of classic books that I wish to read but never have adequate time for.

While we could read others' (or ChatGPT's) summaries, their quality often varies. Why not instruct our GPT-3.5 model to read and summarize them for me?

Forget about the reinforcement learning with human feedback and other black magic. I find the concept of first summarizing small sections of a book, then summarizing those summaries into a higher-level summary, and so on quite useful for getting quality summaries.

I aim to try this method on a small dataset, and if the results are good, perhaps we could open-source our summaries or create some colorful books with other generative AIs. Who knows?

📖 Book List

1. Artificial Intelligence: A Very Short Introduction (2018)
2. Letters to his Son, by The Earl of Chesterfield (Coming soon)