LESSWRONG
LW

Clément L — LessWrong

I just got a feedback from the Bluedot Impact's judges, and thought I could share some parts of it :

"Your idea is unique and pretty cool. Trying to align an AI assistant with strict utilitarian principles using the Constitutional AI (CAI) method is fascinating. This experiment gets at one of the big alignment questions—if we could perfectly encode a moral system into an AI, would we actually want to use it?

[...] (basically summarizing the points made in the project)

The prompts used in evaluation are good but fairly standard—what happens with more complex cases? Moral trade-offs involving large numbers of people (e.g., pandemic response strategies). Multi-step reasoning problems (e.g., economic policies that affect... (read more)

Clément L1y

Exactly, that's what I was thinking about too, and I'd say the impact would most likely be positive too.

Clément L's Shortform

Clément L

This is a special post for quick takes (aka "shortform"). Only the owner can create top-level comments.

Clément L1y*Quick Take

Would it be a good idea to make stickers about AI alignment and stick them in the streets, to spread the idea?

I'm thinking about something simple : A nice logo, and something like "Align AI" under it, maybe with a site like safe.ai in small letters under it, or even a QR code that links to a relevant site, for example the Statement on AI risk (https://www.safe.ai/work/statement-on-ai-risk). The sticker could even be a copy of the statement, as it is quite simple yet striking. Maybe something else would be better.

The thing is that most people don't even know the problem of alignment is a thing, and have never heard of it. Most... (read more)

Replying toTracing Typos in LLMs: My Attempt at Understanding How Models Correct Misspellings

Clément L1y

Tracing Typos in LLMs: My Attempt at Understanding How Models Correct Misspellings

Interesting,I like the way you progressed through the different hypotheses in an experimental way. I won't be able to give interesting feedback in more depht though

Replying toComputational irreducibility challenges the simulation hypothesis

Clément L1y

Computational irreducibility challenges the simulation hypothesis

Thanks for your comment. §1 : Okay, you mean something like this, right? I think you're right, maybe the game of life wasn't the best example then.

§2 : I think I agree, but I can't really get why would one need to know which configuration gave rise to our universe.

§ 3 : I'm not sure if i'm answering adequately, but I meant many chaotic phenomena, which probably include stars transforming into supernovae. In that case we arguably can't precisely predict the time of the transformation without fully computing "low level phenomena". But still I can't see why we would need to "distinguish our world from others".

For now I'm not sure to see where you're going after that, i'm sorry ! Maybe i'll think about it again and get it later.

Replying toComputational irreducibility challenges the simulation hypothesis

Clément L2y

Computational irreducibility challenges the simulation hypothesis

Oh, what is this cold fusion flap thing? I didn't knw about it, and can't really find information about it.

I agree, however what I had in mind was that they probably don't just want to make simulations in which individuals can't say wheter they are simulated or not. They may want to run these simulations in accurate and precise way, that gives them predictions. For example they might wonder what would happen if they apply such and such initial conditions to the system, and want to know how it will behave? In that case, they don't want buge either, even though individuals in the simulation won't be able to tell the difference.

Replying toComputational irreducibility challenges the simulation hypothesis

Clément L2y

Computational irreducibility challenges the simulation hypothesis

As I've said in previous comments I'm inclined to think that simulations need that amount of detail to accurately use them to predict the future. In that case maybe that means that I had in mind a different version of the argument, whereas the original Simulation argument does not asume that the capacity to accurately predict the future of certain systems is an important incentive for simulations to be created.

About the quantum part... Indeed it may be impossible to determine the state of the system if it entails quantum randomness. As I wrote :

"let's note that we did not take quantum randomness into account [...]. However, we may be justified not taking... (read more)

Replying toComputational irreducibility challenges the simulation hypothesis

Clément L2y

Computational irreducibility challenges the simulation hypothesis

Familiar indeed and I agree with that, but in order to predict the future state of this universe, they will arguably need to compute it beyond what we could see ourselves: I mean, to reliably determine the state of the universe in the future, they would need to take into account parts of the system that nobody is aware of, because it is still part of the the causal system that will eventually lead to this future state we want predictions about, right?

Replying toComputational irreducibility challenges the simulation hypothesis

Clément L2y

Computational irreducibility challenges the simulation hypothesis

Thanks for the comment. I mostly agree, but I think I use "reducible" in a stronger sense than you do (maybe I should have specified it then) : by reducible I mean something that would not entail any loss of information (like a lossless compression). In the examples you give, some information - that is considered negligeable - is deleted. The thing is that I think these details could still make a difference in the state of the system at time t+Δt, due to how sensitiveness to initial conditions in "real" systems can in the end make big differences. Thus, we have to somehow take into account a high level of detail,... (read more)

Computational irreducibility challenges the simulation hypothesis

Clément L

Introduction

In this post I will talk about the simulation argument, originally coming from Nick Bostrom and reformulated by David Chalmers. I will try to argue that taking into account the computational irreducibility principle, we are less likely to live in a simulated world. More precisely, this principle acts as a sim-blocker, an element that would make large simulations including conscious beings like us less likely to exist.

First, we will summarize the simulation argument and explain what sim-blockers are, and what are the main ones usually considered. Then, we will explain what the computational irreducibility is, and how it constitutes a sim-blocker. Lastly, we will try to adress potential critics and limitations of... (read 1839 more words →)

Epiphenomenalism leads to eliminativism about qualia

Clément L

Introduction

In this post I will explain why I think that certain forms of realism about conscious experience face some issues that ultimately lead them to the conclusion that our belief that consciousness exists is not reliable, and thus consciousness may not exist at all, as counterintuitively as it seems. This conclusion is similar to the one given by the illusionist theory of consciousness, a kind of eliminativism about qualia, which entails that conscious experience does not exist.

A brief presentation of epiphenomenalism and illusionism

Epiphenomenalism

First of all, we need to briefly define what these two views consists in. This is the definition of epiphenomenalism found of Wikipedia :

Epiphenomenalism is a position on the mind–body

... (read 1884 more words →)

LESSWRONG
LW

LESSWRONG
LW

Clément L

Utilitarian AI Alignment: Building a Moral Assistant with the Constitutional AI Method

Computational irreducibility challenges the simulation hypothesis

Epiphenomenalism leads to eliminativism about qualia

Clément L's Shortform

Clément L

Clément L

Clément L's Shortform

Utilitarian AI Alignment: Building a Moral Assistant with the Constitutional AI Method

Computational irreducibility challenges the simulation hypothesis

Epiphenomenalism leads to eliminativism about qualia

Clément L

Utilitarian AI Alignment: Building a Moral Assistant with the Constitutional AI Method

Computational irreducibility challenges the simulation hypothesis

Epiphenomenalism leads to eliminativism about qualia

Clément L's Shortform

Clément L

Clément L

Clément L's Shortform

Utilitarian AI Alignment: Building a Moral Assistant with the Constitutional AI Method

Computational irreducibility challenges the simulation hypothesis

Epiphenomenalism leads to eliminativism about qualia

Introduction

Introduction

A brief presentation of epiphenomenalism and illusionism

Epiphenomenalism