AI Alignment Graph

---

🗓️ 1st August 2024

🥇 We are proud to announce that we secured First Place at the prestigious Research Augmentation Hackathon: Supercharging AI Alignment event!

---

👉 Check out the live version here: AI Alignment Research Graph

👋🏻 Getting Started & Join Our Community

Whether you're a newcomer or a seasoned researcher, we have a place for you in our community. Here are some ways to get started:

	Visit the website
	Join our Discord community!

Important

Star Us, to get updates from GitHub ~ ⭐️

Features

• Interactive graph visualization of AI Alignment Research
• High-Quality LLM-based segementation of papers
• Search for papers by title, author, or abstract
• Filter by year, source, and category
• Click on a node to view a summary of the topic

Local Build

To build locally

# node lts/iron
npm i
npx quartz build --serve

Troubleshooting

if you get ADDRINUSE: address already in use :::8080 run

npx kill-port 8080

Development Notes:

• the content folder stores the markdown files that represents the graph strucuture
• the generate_md folder contains the code to generate the .md files
• generating .md files requires ai-alignement-dataset-jsonl-file to be placed under generate_md/dataset folder
• generating .md files requires a anthropic api key to be stored in /generate_md/.env file

Contributors

... add contributor graph here

Acknowledgements

• Thanks to alignment-research-dataset for the dataset
• Built using Quartz v4
• Commits prior to commit hash #5c7cb55 come from the quartz v4 web framework, this is to allow easier updates of the web-framework using git pull upstream

         

---

TODO:

• Refactor the code in explore_ds.py to output in json and not yaml format
• Impove the code in llm_cluster.py to take a batch of papers (eg. 20) in each call to the LLM instead
• run llm_cluster.py on the entire source

Improvements:

• explore_ds.py currently filters by arxiv papers, could also support other sources
• Chatbot to the right side of the page for some questioning...