x

LESSWRONG

LW

Lysandre Terrisse

Top postsTop post

Lysandre Terrisse

Message

I'm a 21 years old university student who tries to be a good AI Safety researcher.

If you haven't yet, check out the Compendium: http://pdf.thecompendium.ai/the_compendium.pdf

89

8

4

3y

Lysandre Terrisse

I'm a 21 years old university student who tries to be a good AI Safety researcher.

If you haven't yet, check out the Compendium: http://pdf.thecompendium.ai/the_compendium.pdf

Lysandre Terrisse — LessWrong

Top postsTop post

Planning to build a cryptographic box with perfect secrecy

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, and finally, I will mention some ethical concerns about this cryptographic box. Before reading this post, I recommend you to read this post by Paul Christiano, and the comments that go with it. These are very informative, and they sharpened my views for this project. Paul Christiano presents a way to extract a friendly AI from an unfriendly one. This being only one example of what can be done with a cryptographic box, I will mostly consider cryptographic boxes as a solution to a problem that I call the malign computation problem. Introduction In August 2022, I started reading AGI Safety Literature Review. At one point, the authors tell this: > One way to box an AGI is to homomorphically encrypt it. Trask (2017) shows how to train homomorphically encrypted neural networks. By homomorphically encrypting an AGI, its predictions and actions also come out encrypted. A human operator with the secret key can choose to decrypt them only when he wants to. When I have read this for the first time, I told myself that I should check this work because it seemed important. And

Disproving and partially fixing a fully homomorphic encryption scheme with perfect secrecy

My Short Summary of the OpenAI Agent Swarm Incidents

My recommended resources for AI safety, alignment, and existential risks

My Short Summary of the OpenAI Agent Swarm Incidents

(Over the last month, I have read every report and document I could find about agent swarms and summarized them. I intend to keep this page updated for new reports and findings.) On July 16, Hugging Face writes Security incident disclosure — July 2026, where they claim that, earlier that...

My recommended resources for AI safety, alignment, and existential risks

I have studied AI safety and existential risks for the last four years and, in this post, I share the resources I liked reading/watching the most. I have read/watched all of them. A few of these resources are in French. Not all the articles are peer-reviewed. I will update this...

A Solution to Cryptographic Boxes for Unfriendly AI

Summary In 2010, Paul Christiano wrote Cryptographic Boxes for Unfriendly AI, in which he asks how we can sandbox arbitrarily dangerous AIs and recommends Homomorphic Encryption as a potential solution. However, Homomorphic Encryption relies on computational assumptions (it does not provide perfect secrecy) and is extremely slow. The question then...

How could I tell someone that consciousness is not the primary concern of AI Safety?

In the PDF version of the Dive into Deep Learning book, at page 27, we can read this: > Frequently, questions about a coming AI apocalypse and the plausibility of a singularity have been raised in non-technical articles. The fear is that somehow machine learning systems will become sentient and...

Jun 13, 2025•11

Is OpenAI net negative for AI Safety?

I recently saw a post arguing that top AI labs should shut down. This let me wonder whether the AI Safety community thinks OpenAI is net negative for AI safety. I chose OpenAI because I consider it as the most representative top AI lab (in the sense that, if we...

Nov 2, 2024•4

Thirty random thoughts about AI alignment

Why does this post exist? In order to learn more about my own opinion about AI safety, I tried to write a thought every day before going to bed. Of course, I failed doing this every day, and this is the reason why I have only thirty arguments since January....

Sep 15, 2024•6

Disproving and partially fixing a fully homomorphic encryption scheme with perfect secrecy

Summary In the last blog post, I introduced my plan to make the safest cryptographic box in the world, and to make it widely available. This would, in theory, make it possible to run infinitely dangerous programs (including superintelligences) safely. This cryptographic box was supposed to use a scheme that...

May 26, 2024•16

Load More (7/8)