5th generation military aircraft are extremely optimised to reduce their radar cross section. It is this ability above all others that makes the f-35 and the f-22 so capable - modern anti aircraft weapons are very good, so the only safe way to fly over a well defended area is not to be seen.

But wouldn't it be fairly trivial to detect a stealth aircraft optically?

This is what an f-35 looks like from underneath at about 10 by 10 pixels:

You and I can easily tell what that is (take a step back, or squint). So can GPT4:

The image shows a silhouette of a fighter jet in the sky, likely flying at high speed. The clear blue sky provides a sharp contrast, making the aircraft's dark outline prominent. The

Abstract:

Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"), KANs have learnable activation functions on edges ("weights"). KANs have no linear weights at all -- every weight parameter is replaced by a univariate function parametrized as a spline. We show that this seemingly simple change makes KANs outperform MLPs in terms of accuracy and interpretability. For accuracy, much smaller KANs can achieve comparable or better accuracy than much larger MLPs in data fitting and PDE solving. Theoretically and empirically, KANs possess faster neural scaling laws than MLPs. For interpretability, KANs can be intuitively visualized and can easily interact with human users. Through two examples in mathematics and physics, KANs are shown to be useful collaborators helping scientists (re)discover mathematical and physical laws. In summary, KANs are promising alternatives for MLPs, opening opportunities for further improving today's deep learning models which rely heavily on MLPs.

When I introduce people to plans like QACI, they often have objections like "How is an AI going to do all of the simulating necessary to calculate this?" or "If our technology is good enough to calculate this with any level of precision, we can probably just upload some humans." or just "That's not computable."

I think these kinds of objections are missing the point of formal goal alignment and maybe even outer alignment in general.

To formally align an ASI to human (or your) values, we do not need to actually know those values. We only need to strongly point to them.

AI will figure out our values. Whether it's aligned or not, a recursively self-improving AI will eventually get a very good model of our values, as part...

A classic problem with Christianity is the so-called ‘problem of evil’—that friction between the hypothesis that the world’s creator is arbitrarily good and powerful, and a large fraction of actual observations of the world.

Coming up with solutions to the problem of evil is a compelling endeavor if you are really rooting for a particular bottom line re Christianity, or I guess if you enjoy making up faux-valid arguments for wrong conclusions. At any rate, I think about this more than you might guess.

And I think I’ve solved it!

Or at least, I thought of a new solution which seems better than the others I’ve heard. (Though I mostly haven’t heard them since high school.)

The world (much like anything) has different levels of organization. People are made of...

This is a companion piece to “Why I am no longer thinking about/working on AI safety.” I gave Claude a nearly-complete draft of the post, and asked it to engage with it with its intended audience in mind. I was pleasantly surprised at the quality of its responses. After a back-and-forth about the arguments laid forth in the post, I thought it might be interesting to ask Claude how it thought certain members of this community would respond to the post. I figured it might be interesting to post the dialogue here in case there’s any interest, and if Eliezer, Rohin, or Paul feel that the model has significantly misrepresented their would-be views on my post in its estimation, I would certainly be interested in learning their...

For the last month, @RobertM and I have been exploring the possible use of recommender systems on LessWrong. Today we launched our first site-wide experiment in that direction. 

(In the course of our efforts, we also hit upon a frontpage refactor that we reckon is pretty good: tabs instead of a clutter of different sections. For now, only for logged-in users. Logged-out users see the "Latest" tab, which is the same-as-usual list of posts.)

Why algorithmic recommendations?

A core value of LessWrong is to be timeless and not news-driven. However, the central algorithm by which attention allocation happens on the site is the Hacker News algorithm^[1], which basically only shows you things that were posted recently, and creates a strong incentive for discussion to always be...

I've been going through the FAR AI videos from the alignment workshop in December 2023. I'd like people to discuss their thoughts on Shane Legg's 'necessary properties' that every AGI safety plan needs to satisfy. The talk is only 5 minutes, give it a listen:

Otherwise, here are some of the details:

All AGI Safety plans must solve these problems (necessary properties to meet at the human level or beyond):

1. Good world model
2. Good reasoning
3. Specification of the values and ethics to follow

All of these require good capabilities, meaning capabilities and alignment are intertwined.

Shane thinks future foundation models will solve conditions 1 and 2 at the human level. That leaves condition 3, which he sees as solvable if you want fairly normal human values and ethics.

Shane basically thinks that if the above...