Summary.

Since September 2023, I started learning a lot of math and programming skills in order to develop the safest cryptographic box in the world (and yes, I am aiming high). In these four months, I learned important things you may want to know:

Fully Homomorphic Encryption (FHE) schemes with perfect secrecy do exist.
These FHE schemes do not need any computational assumption.
These FHE schemes are tractable (in the worst case, encrypting a program before running it makes it three times slower).
We can therefore run infinitely dangerous programs without obtaining any information about them or their outputs. This may be useful in order to run a superintelligence without destroying the world.
However, these schemes work only on quantum computers.

In this post, I will firstly talk about how I learned about this FHE scheme, then I will explain my plan for making this cryptographic box [...]

---

Outline:

(03:01) Trasks work

(04:49) What we would want

(09:15) The plan

(11:14) Where I am right now

(12:49) Ethical concern 1: A cryptographic box is far from sufficient in order to ensure that a superintelligence is safe.

(17:24) Ethical concern 2: Malevolent actors may use cryptographic boxes to cause harm.

(18:40) Conclusion

---

First published:
December 31st, 2023

Source:
https://www.lesswrong.com/posts/TK8ptSJGvAqj2HaRr/planning-to-build-a-cryptographic-box-with-perfect-secrecy

---

Narrated by TYPE III AUDIO.

“Planning to build a cryptographic box with perfect secrecy” by Lysandre Terrisse

LessWrong (30+ Karma)