AI Safety Communities has a comprehensive list. Some good specific suggestions include:
-
A local student or meetup LessWrong or Effective Altruism group (or start one!)
-
AGI Safety Fundamentals which gives you a cohort to learn alongside and mentorship
-
EleutherAI Discord - ML hacker collective focused on alignment and open-source projects.
-
The relevant discussion threads on the Astral Codex Ten Substack, which sometimes discusses alignment.
Or book free calls with AI Safety Support.