If you want to do technical AI alignment research, you'll need some amount of non-trivial math knowledge. It may be more theoretical, or with more ML/biology grounding, but it'll definitely be math.

How do you learn all this math?

"Self-teaching" is almost a misnomer, compared to just "learning". I don't need to distill something for others, I only need myself to grok it. I may use distillation or adjacent techniques to help myself grok it, but like any N=1 self-experiment, it only needs to work for me. [1]

So then... what helps me understand things?

Formal rules that are written precisely
Wordy concepts that one could use in an essay

Math is technically the former, but real mathematicians (even the great ones!) actually use it more like the latter. That is, they use a lot of "intuition" built up over time.

You can't survive on intuition alone (unless [...]

---

Outline:

(02:26) Tangent (for large grantmakers and orgs only)

(03:38) The Challenge

The original text contained 3 footnotes which were omitted from this narration.

---

First published:
January 9th, 2024

Source:
https://www.lesswrong.com/posts/E6JYCiKYd37EJHbqB/learning-math-in-time-for-alignment

---

Narrated by TYPE III AUDIO.

“Learning Math in Time for Alignment” by NicholasKross

LessWrong (30+ Karma)

“Learning Math in Time for Alignment” by NicholasKross