Hacker News new | past | comments | ask | show | jobs | submit login

> Move to a sphere and it improves to cube root.

No, it doesn't. Due to the Bekenstein bound, the amount of matter — and hence information — that can be stored in a sphere is ultimately proportional to surface area, not to volume. This is covered in part 2 of the article: https://www.ilikebigbits.com/2014_04_28_myth_of_ram_2.html




This is only as you near the theoretical limit of density, though, right? At easy-to-achieve densities that we would be using in the foreseeable future, if we plotted their access times in these different configurations, wouldn't it--practically speaking--still scale at the cube root?

I guess that was covered in the comment.

> This applies even without hitting theoretical information density limits, whatever your best process size and latency.

But now I guess I don't understand why... :(. I feel like we can almost trivially show this isn't true by starting with a downright primitive "best process size"--maybe a system where every bit is so large I can see it and access it using a pair of tweezers--but maybe I am fooling myself?




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: