About MAIS
Math for AI Safety is an open research organization. We state open problems whose solutions would advance AI safety, precisely enough for a mathematician outside the area to work on. Each one is paired with a theory of change: how a solution would help.
Open by default
Other attempts to automate alignment research are run behind closed doors. Here the problems, the submissions, the reviews and the verdicts are public.
When is a problem open?
A problem is listed as open if it is open to our knowledge. It is checked against the literature when it is released, and finding an existing solution counts as resolving it.
From problem to paper
Open problems are incorporated into agendas, and a maturing agenda spins off papers. Every document carries a permanent identifier, MAIS-O, MAIS-A or MAIS-P, which never changes even if the title does.
Taking part
- Open an issue naming the problem, before investing serious work.
- Post partial or numerical results, labeled as such.
- A maintainer reviews it in public and records what was checked and what was not.
- Verified work is credited as printed on your write-up.
Contribution guide ↗ · How to cite ↗
AI assistance
AI coauthors are welcome. If an AI produced the argument, say so: such submissions are labeled and screened first, and every claim is still verified by a person.
Team
Professor of Mathematics, Cornell University