Explain one safety idea to a friend
Write a short, jargon-free explainer of one AI safety idea (reward hacking, sycophancy, compute governance, DNA screening) for someone outside tech.
Define ten key terms from the theme you’re most curious about, in one sentence each with an everyday example, then compare them with the site’s glossary.
Vocabulary is the first barrier for newcomers. Writing definitions yourself is the fastest way through it, and the result helps the next person.
Output: A one-page glossary.
Pick one of the five themes.
Skim a beginner reading or two and note the words you had to look up.
One sentence each, plus an everyday example. No definition may use another unexplained term.
Compare with this site’s glossary. Where is yours clearer? Where did you get it wrong?
All steps done
Share what you made, then try another project. The PDF version has room for notes.
Write a short, jargon-free explainer of one AI safety idea (reward hacking, sycophancy, compute governance, DNA screening) for someone outside tech.
Pick a beginner-friendly paper linked from any project on this site and summarise it in ten clear posts: the question, what they did, what they found, and why it matters.
Far-UVC light might kill airborne germs in occupied rooms. Write the clear, honest explainer the field is missing: what it is, how it works, what the evidence says, and what is still uncertain.
Neel Nanda’s list of 200 open problems grades each one by difficulty, including problems marked as good for beginners. Pick one, scope it down and investigate with TransformerLens.