Nine months ago we, RAISE, have started creating a Math Prerequisites for AI Safety online course. It has mostly MIRI research related subjects: set theory, computability theory, and logic, but we want to add machine learning related subjects in the future. For 4 months we've been adding new lessons and announcing them on LessWrong. Then we stopped, looked back and decided to improve their usability. That's what we've been busy with since August.
News since the last post
- Big update of 7 levels we had previously published, which you can see in the picture above. The lessons use textbooks, which you will need to follow along. Previously lessons looked like "read that section; now solve problems 1.2, 1.3, 1.4c from the textbook; now solve these additional problems we came up with". Now our lessons still say "read that section", but the problems (and their solutions, in contrast to many textbooks, which don't provide solutions) are included in lessons themselves. Additional problems are now optional, and we recommend that students skip them by default and do them only if they need more practice. New levels in Logic, Set Theory, and Computability tracks will be like that as well.
- Level 1 was very long, consisted of 45 pages of reading, and could take 10 hours for someone unfamiliar with logic. We separated it into smaller parts.
- Two new levels. Level 8.1: Proof by Induction. Level 8.2: Abacus Computability.
If you study using our course, please give us feedback. Leave a comment here or email us at firstname.lastname@example.org, or through the contact form. Do you have an idea about what prerequisites are most important for AI Safety research? Do you know an optimal way to learn them? Tell us using the same methods or collaborate with us.
Can you check if a mathematical proof is correct? Do you know how to make proofs understandable and easy to remember? Would you like to help to create the prerequisites course? If yes, consider volunteering.