x

LESSWRONG
LW

aelwood — LessWrong

aelwood

Top postsTop post

aelwood

Message

Physicist and AI researcher with a passion for philosophy. Interested in consciousness, models of reality, meditation, and how we should choose to live and act. Writing over at https://pursuingreality.com

1

5

3

6y

aelwood

Physicist and AI researcher with a passion for philosophy. Interested in consciousness, models of reality, meditation, and how we should choose to live and act. Writing over at https://pursuingreality.com

The second bitter lesson — there’s a fundamental problem with aligning distributed AI

Note: this the first part of an essay on my substack, check out the full essay to see the solutions I put forward When Richard Sutton introduced the bitter lesson for AI in 2019, he broke the myth that great human ingenuity is needed to create intelligent machines. All it...

Jan 19, 2025•-5

Utilitarianism is the only option

Note: I wrote this post before the FTX collapse resulted in lots of people questioning utilitarian principles, so it isn't a response to any of that, although I think it is relevant. It may be a bit more speculative than some people are comfortable with, and isn't a fully fleshed...

Dec 3, 2022•-12

A stubborn unbeliever finally gets the depth of the AI alignment problem

> I realise posting this here might be preaching to the converted, but I think it could be interesting for some people to see a perspective from someone slow to get onboard with worrying about AI alignment. I’m one of those people that finds it hard to believe that misaligned...

Oct 13, 2022•17

A hierarchy of truth

In this article I want to offer a framework for thinking about truth. I’m not offering a metaphysical theory - I’ll leave that to academic philosophers - but a useful way of relating to the different truth claims people make in everyday life. As a rationalist thinking about truth, I...

May 11, 2020•4

The ways of knowing

When trying to understand the nature of reality, we have to grapple with the question of how it is that we can know something of it. As we are limited to view the universe through a human lens, it is not clear how our mental constructs correspond to reality. To...

May 5, 2020•1

Top postsTop post

A stubborn unbeliever finally gets the depth of the AI alignment problem

> I realise posting this here might be preaching to the converted, but I think it could be interesting for some people to see a perspective from someone slow to get onboard with worrying about AI alignment. I’m one of those people that finds it hard to believe that misaligned Artificial General Intelligence (AGI) could destroy the world. Even though I’ve understood the main arguments and can’t satisfyingly refute them, a part of my intuition won’t easily accept that it’s an impending existential threat. I work on deploying AI algorithms in industry, so have an idea of both how powerful and limited they can be. I also get why AI safety in general should be taken seriously, but I struggle to feel the requisite dread. The best reason I can find for my view is that there is a lot of “Thinkism” in arguments for AGI takeoff. Any AGI that wants to make an influence outside of cyberspace, e.g. by building nanobots or a novel virus, will ultimately run into problems of computational irreducibility — it isn’t possible to model everything accurately, so empirical work in the physical world will always be necessary. These kind of experiments are slow, messy and resource intensive. So, any AGI is going to reach some limits when it tries to influence the physical world. I do realise there are loads of ways an AGI can cause a lot of damage without requiring the invention of new physical technologies, but this still slowed things down enough for me to worry less about alignment issues. That was, until I started realising that alignment problems aren’t limited to the world of AI. If you look around you can see them everywhere. The most obvious example is climate change — there is a clear misalignment between the motivations of the petroleum industry and the long term future of humanity, which causes a catastrophic problem. The corporate world is full of such alignment problems, from the tobacco industry misleading the public about the harms of smoking to social media companies

A hierarchy of truth

The ways of knowing

The second bitter lesson — there’s a fundamental problem with aligning distributed AI