Submitting your AI alignment project
Submit your project on the course hub. Put the final touches on your project, and submit it to us for judging! We recommend spending the majority of your efforts after session 11 on creating the final deliverable. You should produce a public product such as:
- a blog post (e.g. on Google Sites, WordPress.com, LessWrong, or Substack)
- You can use our research project blog post template
- a website (e.g. on GitHub Pages, Notion or Squarespace)
- a video (e.g. on YouTube)
- some combination of the above
- something else entirely
Attend the project closing event. We’ll announce the winners of the project competition, award prizes, and close out the course. You can sign up for the event on the course hub.
Tips on creating an excellent final product
Review our evaluation criteria. Think about how you can produce an output that we'll score highly: we think in general this will result in a strong project output.
Communicate well. Your output should be easy to understand. If in doubt, aim for a smart high-schooler with some machine learning background. You should:
- use plain English (this doesn't mean you need to dumb down your project)
- define key terms, or link to good definitions of them
- structure writing with headers, topic sentences and lists
Explain what you found out, and how this contributes to AI safety. A common mistake is to write about the work you put in, rather than what you discovered out of it. Also, negative results (where you discovered something didn’t work) are useful research!
Ask for feedback. You can reach out to cohort members, your facilitator, or people you met at course networking events. A great tactic is to ask them to explain what they think your project is after reading - this often highlights where your product isn't as clear as you thought it might be.