All of jaan's Comments + Replies
From Bennett et el's reply to the aestivation paper:
Thus we come to our first conclusion: a civilization can freely erase bits without forgoing larger future rewards up until the point when all accessible bounded resources are jointly thermalized.
They don't mention black holes specifically, but my interpretation of this is that a civilization can first dump waste heat into a large black hole, and then later when the CMB temperature drops below that of the black hole, reverse course to use Hawking radiation of the black hole as energy source and CMB as ...
thank you for continuing to stretch the overton window! note that, luckily, the “off-switch” is now inside the window (though just barely so, and i hear that big tech is actively - and very myopically - lobbying against on-chip governance). i just got back from a UN AIAB meeting and our interim report does include the sentence “Develop and collectively maintain an emergency response capacity, off-switches and other stabilization measures” (while rest of the report assumes that AI will not be a big deal any time soon).
3thanks! basically, i think that the top priority should be to (quickly!) slow down the extinction race. if that’s successful, we’ll have time for more deliberate interventions — and the one you propose sounds confidently net positive to me! (with sign uncertainties being so common, confident net positive interventions are surprisingly rare).
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.
OK hmm I think I understand what you mean.
I would have thought about it like this:
- "our reference class" includes roughly the observations we make before observing that we're very early in the universe
- This includes stuff like being a pre-singularity civilization
- The anthropics here suggest there won't be lots of civs later arising and being in our reference class and then finding that they're much later in universe histories
- It doesn't speak to the existence or otherwise of future human-observer moments in a post-singularity civilization
... but as you say anthropics is confusing, so I might be getting this wrong.
1three most convincing arguments i know for OP’s thesis are:
-
atoms on earth are “close by” and thus much more valuable to fast running ASI than the atoms elsewhere.
-
(somewhat contrary to the previous argument), an ASI will be interested in quickly reaching the edge of the hubble volume, as that’s slipping behind the cosmic horizon — so it will starlift the sun for its initial energy budget.
-
robin hanson’s “grabby aliens” argument: witnessing a super-young universe (as we do) is strong evidence against it remaining compatible with biological life for l
i would love to see competing RSPs (or, better yet, RTDPs, as @Joe_Collman pointed out in a cousin comment).
Sure, but I guess I would say that we're back to nebulous territory then—how much longer than six months? When if ever does the pause end?
i agree that, if hashed out, the end criteria may very well resemble RSPs. still, i would strongly advocate for scaling moratorium until widely (internationally) acceptable RSPs are put in place.
I'd very surprised if there was substantial x-risk from the next model generation.
i share the intuition that the current and next LLM generations are unlikely an xrisk. however, i don't trust my (or anyone else's) intuitons stron...
the FLI letter asked for “pause for at least 6 months the training of AI systems more powerful than GPT-4” and i’m very much willing to defend that!
my own worry with RSPs is that they bake in (and legitimise) the assumptions that a) near term (eval-less) scaling poses trivial xrisk, and b) there is a substantial period during which models trigger evals but are existentially safe. you must have thought about them, so i’m curious what you think.
that said, thank you for the post, it’s a very valuable discussion to have! upvoted.
the werewolf vs villager strategy heuristic is brilliant. thank you!
if i understand it correctly (i may not!), scott aaronson argues that hidden variable theories (such as bohmian / pilot wave) imply hypercomputation (which should count as an evidence against them): https://www.scottaaronson.com/papers/npcomplete.pdf
interesting, i have bewelltuned.com in my reading queue for a few years now -- i take your comment as an upvote!
myself i swear by FDT (somewhat abstract, sure, but seems to work well) and freestyle dancing (the opposite of abstract, but also seems to work well). also coding (eg, just spent several days using pandas to combine and clean up my philanthropy data) -- code grounds one in reality.
having seen the “kitchen side” of the letter effort, i endorse almost all zvi’s points here. one thing i’d add is that one of my hopes urging the letter along was to create common knowledge that a lot of people (we’re going to get to 100k signatures it looks like) are afraid of the thing that comes after GPT4. like i am.
thanks, everyone, who signed.
EDIT: basically this: https://twitter.com/andreas212nyc/status/1641795173972672512
while it’s easy to agree with some abstract version of “upgrade” (as in try to channel AI capability gains into our ability to align them), the main bottleneck to physical upgrading is the speed difference between silicon and wet carbon: https://www.lesswrong.com/posts/Ccsx339LE9Jhoii9K/slow-motion-videos-as-ai-risk-intuition-pumps
yup, i tried invoking church-turing once, too. worked about as well as you’d expect :)
looks great, thanks for doing this!
one question i get every once in a while and wish i had a canonical answer to is (probably can be worded more pithily):
"humans have always thought their minds are equivalent to whatever's their latest technological achievement -- eg, see the steam engines. computers are just the latest fad that we currently compare our minds to, so it's silly to think they somehow pose a threat. move on, nothing to see here."
note that the canonical answer has to work for people whose ontology does not include the concepts of "computation"...
the potentially enormous speed difference (https://www.lesswrong.com/posts/Ccsx339LE9Jhoii9K/slow-motion-videos-as-ai-risk-intuition-pumps) will almost certainly be an effective communications barrier between humans and AI. there’s a wonderful scene of AIs vs humans negotiation in william hertling’s “A.I. apocalypse” that highlights this.
i agree that there's the 3rd alternative future that the post does not consider (unless i missed it!):
3. markets remain in an inadequate equilibrium until the end of times, because those participants (like myself!) who consider short timelines remain in too small minority to "call the bluff".
see the big short for a dramatic depiction of such situation.
great post otherwise. upvoted.
yeah, this seems to be the crux: what will CEV prescribe for spending the altruistic (reciprocal cooperation) budget on. my intuition continues to insist that purchasing the original star systems from UFAIs is pretty high on the shopping list, but i can see arguments (including a few you gave above) against that.
oh, btw, one sad failure mode would be getting clipped by a proto-UFAI that’s too stupid to realise it’s in a multi-agent environment or something,
ETA: and, tbc, just like interstice points out below, my “us/me” label casts a wider net than “us in this particular everett branch where things look particularly bleak”.
roger. i think (and my model of you agrees) that this discussion bottoms out in speculating what CEV (or equivalent) would prescribe.
my own intuition (as somewhat supported by the moral progress/moral circle expansion in our culture) is that it will have a nonzero component of “try to help out the fellow humans/biologicals/evolved minds/conscious minds/agents with diminishing utility function if not too expensive, and especially if they would do the same in your position”.
tbc, i also suspect & hope that our moral circle will expand to include all fellow sentients. (but it doesn't follow from that that paying paperclippers to unkill their creators is a good use of limited resources. for instance, those are resources that could perhaps be more efficiently spent purchasing and instantiating the stored mindstates of killed aliens that the surviving-branch humans meet at the edge of their own expansion.)
but also, yeah, i agree it's all guesswork. we have friends out there in the multiverse who will be willing to give us some...
yeah, as far as i can currently tell (and influence), we’re totally going to use a sizeable fraction of FAI-worlds to help out the less fortunate ones. or perhaps implement a more general strategy, like mutual insurance pact of evolved minds (MIPEM).
this, indeed, assumes that human CEV has diminishing returns to resources, but (unlike nate in the sibling comment!) i’d be shocked if that wasn’t true.
one thing that makes this tricky is that, even if you think there's a 20% chance we make it, that's not the same as thinking that 20% of Everett branches starting in this position make it. my guess is that whether we win or lose from the current board position is grossly overdetermined, and what we're fighting for (and uncertain about) is which way it's overdetermined. (like how we probably have more than one in a billion odds that the light speed limit can be broken, but that doesn't mean that we think that one in every billion photons breaks the limit.) ...
1sure, this is always a consideration. i'd even claim that the "wait.. what about the negative side effects?" question is a potential expected value spoiler for pretty much all longtermist interventions (because they often aim for effects that are multiple causal steps down the road), and as such not really specific to software.
great idea! since my metamed days i’ve been wishing there was a prediction market for personal medical outcomes — it feels like manifold mechanism might be a good fit for this (eg, at the extreme end, consider the “will this be my last market if i undertake the surgery X at Y?” question). should you decide to develop such aspect at one point, i’d be very interested in supporting/subsidising.
actually, the premise of david brin’s existence is a close match to moravec’s paragraph (not a coincidence, i bet, given that david hung around similar circles).
confirmed. as far as i can tell (i’ve talked to him for about 2h in total) yi really seems to care, and i’m really impressed by his ability to influence such official documents.
indeed, i even gave a talk almost a decade ago about the evolution:humans :: humans:AGI symmetry (see below)!
what confuses me though is that "is general reasoner" and "can support cultural evolution" properties seemed to emerge pretty much simultaneously in humans -- a coincidence that requires its own explanation (or dissolution). furthermore, eliezer seems to think that the former property is much more important / discontinuity causing than the latter. and, indeed, outsized progress being made by individual human reasoners (scientists/inventors/etc.) see...
amazing post! scaling up the community of independent alignment researchers sounds like one of the most robust ways to convert money into relevant insights.
indeed they are now. retrocausality in action? :)
well, i've always considered human life extension as less important than "civilisation's life extension" (ie, xrisk reduction). still, they're both very important causes, and i'm happy to support both, especially given that they don't compete much for talent. as for the LRI specifically, i believe they simply haven't applied to more recent SFF grant rounds.
correct! i’ve tried to use this symmetry argument (“how do you know you’re not the clone?”) over the years to explain the multiverse: https://youtu.be/29AgSo6KOtI?t=869