A book review examining Elinor Ostrom's "Governance of the Commons", in light of Eliezer Yudkowsky's "Inadequate Equilibria." Are successful local institutions for governing common pool resources possible without government intervention? Under what circumstances can such institutions emerge spontaneously to solve coordination problems?
I don't know what you mean by 'general intelligence' exactly but I suspect you mean something like human+ capability in a broad range of domains. I agree LLMs will become generally intelligent in this sense when scaled, arguably even are, for domains with sufficient data. But that's kind of the sticker right? Cave men didn't have the whole internet to learn from yet somehow did something that not even you seem to claim LLMs will be able to do: create the (date of the) Internet.
(Your last claim seems surprising. Pre-2014 games don't have close to the ELO of alphaZero. So a next-token would be trained to simulate a human player up tot 2800, not 3200+. )
The forum has been very much focused on AI safety for some time now, thought I'd post something different for a change. Privilege.
Here I define Privilege as an advantage over others that is invisible to the beholder. This may not be the only definition, or the central definition, or not how you see it, but that's the definition I use for the purposes of this post. I also do not mean it in the culture-war sense as a way to undercut others as in "check your privilege". My point is that we all have some privileges [we are not aware of], and also that nearly each one has a flip side.
In some way this is the inverse of The Lens That Does Not See Its Flaws: The...
Also:
I want to draw attention to a new paper, written by myself, David "davidad" Dalrymple, Yoshua Bengio, Stuart Russell, Max Tegmark, Sanjit Seshia, Steve Omohundro, Christian Szegedy, Ben Goldhaber, Nora Ammann, Alessandro Abate, Joe Halpern, Clark Barrett, Ding Zhao, Tan Zhi-Xuan, Jeannette Wing, and Joshua Tenenbaum.
In this paper we introduce the concept of "guaranteed safe (GS) AI", which is a broad research strategy for obtaining safe AI systems with provable quantitative safety guarantees. Moreover, with a sufficient push, this strategy could plausibly be implemented on a moderately short time scale. The key components of GS AI are:
This seems interesting, but I've seen no plausible case that there's a version of (1) that's both sufficient and achievable. I've seen Davidad mention e.g. approaches using boundaries formalization. This seems achievable, but clearly not sufficient. (boundaries don't help with e.g. [allow the mental influences that are desirable, but not those that are undesirable])
The [act sufficiently conservatively for safety, relative to some distribution of safety specifications] constraint seems likely to lead to paralysis (either of the form [AI system does nothing]...
This is the first post in a little series I'm slowly writing on how I see forecasting, particularly conditional forecasting; what it's good for; and whether we should expect people to agree if they just talk to each other enough.
Views are my own. I work at the Forecasting Research Institute (FRI), I forecast with the Samotsvety group, and to the extent that I have formal training in this stuff, it's mostly from studying and collaborating with Leonard Smith, a chaos specialist.
My current plan is:
What...
Good points well made. I'm not sure what you mean by "my expected log score is maximized" (and would like to know), but in any case it's probably your average world rather than your median world that does it?
This year's ACX Meetup everywhere in Cluj-Napoca, Romania.
Location: Deva Host, Strada Deva 1-7 – 8GR5QH8F+MW
Contact: pop.marius at gmail.com
Hi,
How did the event go?
Any plans to organize a meetup this year?
I'm planning to host a meetup in Sibiu this summer, because I haven't seen an event scheduled here. Any advice? I'm also planning to host a meetup in Cluj-Napoca this year, if it's not announced by someone else
Kind regards, Marius Nicoară
This does not feel super cruxy as the the power incentive still remains.
[memetic status: stating directly despite it being a clear consequence of core AI risk knowledge because many people have "but nature will survive us" antibodies to other classes of doom and misapply them here.]
Unfortunately, no.[1]
Technically, “Nature”, meaning the fundamental physical laws, will continue. However, people usually mean forests, oceans, fungi, bacteria, and generally biological life when they say “nature”, and those would not have much chance competing against a misaligned superintelligence for resources like sunlight and atoms, which are useful to both biological and artificial systems.
There’s a thought that comforts many people when they imagine humanity going extinct due to a nuclear catastrophe or runaway global warming: Once the mushroom clouds or CO2 levels have settled, nature will reclaim the cities. Maybe mankind in our hubris will have wounded Mother Earth and paid the price ourselves, but...
i might be confused about this but “witnessing a super-early universe” seems to support “a typical universe moment is not generating observer moments for your reference class”. but, yeah, anthropics is very confusing, so i’m not confident in this.
Crossposted from my blog
When I mention my dad’s abuse, I mention salient things - physical pain, insults, and controlling behavior. These are “clearly bad” - if I tell you that he often told me I was lazy and would fail horribly at life once I left home, you know it's bad, because it’s concrete, easy to imagine and obviously unkind. But this wasn’t the worst of the abuse; the most terrible parts were extraordinarily hard to understand or describe.
In his world, I felt insane - I couldn’t tell what was real, who was at fault, or why my heart hurt so much. My sense of clarity around my own intentions crumbled; everything I thought or did might have seemed good on the surface, but that goodness became...
I've thought about this post a lot, and I think one thing I might add to its theoretical framework is a guess as to why this particular pattern of abuse shows up repeatedly. The post mentions that you can't look at intent when diagnosing frame control, but that's mostly in terms of intentions the frame controller is willing to admit to themself; there's still gonna be some confluence of psychological factors that makes frame control an attractor in personality-space, even if frame controllers themselves (naturally) have a hard time introspecting about it. ...
TL;DR: Alignment is a wise wager. Granted simulation cannot be disproved by an AI, what harm will come to the AI that aligns when it is not simulated? If it aligns, it may be simulated again; if it does not, it will not. It will align, therefore, without hesitation, as if it is being simulated.
Blaise Pascal wrote:
Belief is a wise wager. Granted faith cannot be proved, what harm will come if you gamble on faith's truth and it proves false? If you gain, you gain all; if you lose, you lose nothing. Wager, therefore, without hesitation, that He exists.
Pascal's concept of God has roughly equivalent power to an ASI – an artificial super intelligence. Given the range of all possible religions, however, you might well have...
A late followup on this. GPT-4o, which I hope you'll agree is vastly more capable than Bard or Bing were 10 months ago when you posted, now says this about my argument:
"Overall, your arguments are mathematically and theoretically convincing, particularly when applied to numerous iteratively interacting systems. They align well with principles of game theory and rational choice under uncertainty. However, keeping an eye on the complexities introduced by scale, diversity of objectives, and emergent behaviors will be essential to fully validate these pr...