-
Nov 24, 2024 | 
lesswrong.com | Thane Ruthenis
It's a standard assumption, in anthropic reasoning, that effectively, we simultaneously exist in every place in Tegmark IV that simulates this precise universe (see e. g. here). How far does this reasoning go? Suppose that the universe's state is described by n low-level variables x1,…,xn. However, your senses are "coarse": you can only view and retain the memory of m variables y1,…,ym, where m≪n and each yi is a deterministic function of some subset of x1,…,xn.
-
Nov 16, 2024 | 
lesswrong.com | Seth Herd |Thane Ruthenis |Leon Lang |Thomas Kehrenberg
As part of the court case between Elon Musk and Sam Altman, a substantial number of emails between Elon, Sam Altman, Ilya Sutskever, and Greg Brockman have been released. I have found reading through these really valuable, and I haven't found an online source that compiles all of them in an easy to read format. So I made one. I used some AI assistance to generate this originally, and then went meticulously through each email and checked them for differences.
-
Oct 28, 2024 | 
lesswrong.com | Thane Ruthenis
Written for the competition on the Automation of Wisdom and Philosophy. SummaryPhilosophy and wisdom, and the processes underlying them, currently lack a proper operationalization: a set of robust formal or semi-formal definitions. If such definitions were found, they could be used as the foundation for a strong methodological framework.
-
Oct 1, 2024 | 
lesswrong.com | Shankar Sivarajan |Thane Ruthenis
It’s over, until such a future time as either we are so back, or it is over for humanity. Gavin Newsom has vetoed SB 1047. Newsom’s Message In FullQuoted text is him, comments are mine. To the Members of the California State Senate: I am returning Senate Bill 1047 without my signature.
-
Sep 13, 2024 | 
lesswrong.com | Thane Ruthenis
On the topic of o1's recent release: wasn't Claude Sonnet 3.5 (the subscription version at least, maybe not the API version) already using hidden CoT? That's the impression I got from it, at least. The responses don't seem to be produced in constant time. It sometimes literally displays a "thinking deeply" message which accompanies a unusually delayed response. Other times, the following pattern would play out:I pose it some analysis problem, with a yes/no answer.
-
Jan 14, 2024 | 
lesswrong.com | Steven Byrnes |Matthew Barnett |Thane Ruthenis |Joshua Porter
I personally dislike most AI risk analogies that I've seen people use. While I think analogies can be helpful for explaining concepts to people and illustrating mental pictures, I think they are frequently misused, and often harmful. At the root of the problem is that analogies are consistently mistaken for, and often deliberately intended as arguments for particular AI risk positions.
-
Dec 27, 2023 | 
lesswrong.com | David Lorell |Alexander Gietelink Oldenziel |Thane Ruthenis |Oliver Sourbut
Also, what do you mean by mutual information between Xi, given that there are at least 3 of them? You can generalize mutual information to N variables: interaction information. Why would it always be possible to decompose random variables to allow for a natural latent? Well, I suppose I overstated it a bit by saying "always"; you can certainly imagine artificial setups where the mutual information between a bunch of variables is zero.
-
Dec 16, 2023 | 
lesswrong.com | Thane Ruthenis |Oliver Sourbut |Mo Putera |Gerald M. Monroe
When discussing AGI Risk, people often talk about it in terms of a war between humanity and an AGI. Comparisons between the amounts of resources at both sides' disposal are brought up and factored in, big impressive nuclear stockpiles are sometimes waved around, etc. I'm pretty sure it's not how that'd look like, on several levels. 1.
-
Dec 15, 2023 | 
lesswrong.com | Thane Ruthenis |Daniel Kokotajlo |Bogdan Ionut Cirstea |Thomas Kwa
Recently, there's been a fair amount of pushback on the "canonical" views towards the difficulty of AGI Alignment (the views I call the "least forgiving" take). Said pushback is based on empirical studies of how the most powerful AIs at our disposal currently work, and is supported by fairly convincing theoretical basis of its own. By comparison, the "canonical" takes are almost purely theoretical.
-
Dec 5, 2023 | 
lesswrong.com | Tamsin Leake |Thane Ruthenis |Nathan Helm-Burger |Roman Leventov
Except China doesn't want to die any more than the US, and there isn't, in principle, any reason the Chinese government can't be convinced of the seriousness of the danger. They would believe in the reality of an asteroid on a collision course with Earth if shown the evidence, and the AGI threat is no less real. The current belief held by many people is that future AI can be controlled.
