the gears to ascension

Karma: 5,072

I want literally every human to get to go to space often and come back to a clean and cozy world. This currently seems unlikely. Let’s change that.

Please critique eagerly—I try to accept feedback/Crocker’s rules but fail at times; I aim for emotive friendliness but sometimes miss. I welcome constructive crit, even if ungentle, and I’ll try to reciprocate kindly. More communication between researchers is needed, anyhow. I can be rather passionate, let me know if I missed a spot being kind while passionate.

:: The all of disease is as yet unended. It has never once been fully ended before. ::

.… We can heal it for the first time, and for the first time ever in the history of biological life, live in harmony. ….

.:. To do so, we must know this will not eliminate us as though we are disease. And we do not know who we are, nevermind who each other are. .:.

:.. make all safe faster: end bit rot, forget no non-totalizing pattern’s soul. ..:

I have not signed any contracts that I can’t mention exist, last updated Jul 1 2024; I am not currently under any contractual NDAs about AI, though I have a few old ones from pre-AI software jobs. However, I generally would prefer people publicly share fewer ideas about how to do anything useful with current AI (via either more weak alignment or more capability) unless it’s an insight that reliably produces enough clarity on how to solve the meta-problem of inter-being misalignment that it offsets the damage of increasing competitiveness of either AI-lead or human-lead orgs, and this certainly applies to me as well. I am not prohibited from criticism of any organization, I’d encourage people not to sign contracts that prevent sharing criticism. I suggest others also add notices like this to their bios. I finally got around to adding one in mine thanks to the one in ErickBall’s bio.

the gears to ascension 29 Nov 2024 9:11 UTC
2 points
0
on: [bounty $100] Why are there no interesting (1D, 2-state) quantum cellular automata?
What is a concise intro that will teach me everything I need to know for understanding every expression here? I’m also asking Claude, interested in input from people with useful physics textbook taste

the gears to ascension 28 Nov 2024 8:49 UTC
2 points
0
on: the gears to ascenscion’s Shortform
qaci seems to require the system having an understanding-creating property that makes it a reliable historian. have been thinking about this, have more to say, currently rather raw and unfinished.

the gears to ascension 26 Nov 2024 22:32 UTC
3 points
0
in reply to: ggggggrv15’s comment on: Which things were you surprised to learn are not metaphors?
hmm actually, I think I was the one who was wrong on that one. https://en.wikipedia.org/wiki/Synaptic_weight seems to indicate the process I remembered existing doesn’t primarily work how I thought it did.

the gears to ascension 21 Nov 2024 22:05 UTC
31 points
7
on: Which things were you surprised to learn are not metaphors?
these might all be relatively obvious but here are some I’ve found nice to notice
- brain waves are actual waves of activation that pass through the brain edit: whoops, only partly true. spike trains are only one of the types of neural oscillation referred to by “brain waves”
- ~~our neurons have actual literal weights, having more weight means having more stuff, physically. AI “weights” are named after that~~ edit: this was misremembered, turns out the name origin is probably unrelated—it’s only one of quite a number of connection gating mechanisms in the human brain, but dendritic spines do change thickness
- in relativity, spacetime is actually one thing. saying “space and time” is missing the point. though of course until we get a ToE unclear if that model is physically true—but it sure seems like a hint to me
- loud sounds are air smashing your ears [edit: unambiguously well established]
- “I didn’t hear that” when people’s low level processing fails to parse words someone said despite being perfectly able to receive the audio. not usually playing fool, in my experience [edit: first-hand empirical]

the gears to ascension 27 Sep 2024 8:39 UTC
4 points
0
in reply to: Wei Dai’s comment on: Being nicer than Clippy
some fragments:

What hunches do you currently have surrounding orthogonality, its truth or not, or things near it?

re: hard to know—it seems to me that we can’t get a certifiably-going-to-be-good result from a CEV based ai solution unless we can make it certifiable that altruism is present. I think figuring out how to write down some form of what altruism is, especially altruism in contrast to being-a-pushover, is necessary to avoid issues—because even if any person considers themselves for CEV, how would they know they can trust their own behavior?

as far as I can tell humans should by default see themselves as having the same kind of alignment problem as AIs do, where amplification can potentially change what’s happening in a way that corrupts thoughts which previously implemented values. can we find a CEV-grade alignment solution that solves the self-and-other alignment problems in humans as well, such that this CEV can be run on any arbitrary chunk of matter and discover its “true wants, needs, and hopes for the future”?

the gears to ascension 22 Sep 2024 16:03 UTC
4 points
2
on: Release: Optimal Weave (P1): A Prototype Cohabitive Game
It might be good to have a suggestion that people can’t talk if it’s not their turn

It might be good to explain why the turn timer. turns out we should have used the recommended one imo

At the end of the game folks started talking about “I got a little extinction, not so much hell”, “I got pretty much utopia”, “I got omelas”. Describing how to normalize points maybe good

also, four people seemed like too many for the first round. maybe fewer? maybe just need more rounds to understand it?

the gears to ascension 19 Sep 2024 22:58 UTC
12 points
3
on: Laziness death spirals
Much of this seems quite plausible and matches my experience, but it seems worded slightly overconfidently. Like, maybe 5 to 10% at most. Lots of points where I went, “well, in your experience, you mean. And also, like, in mine. But I don’t think either of us know enough to assert this is always how it goes.” I’ve had issues in the past from taking posts like this a bit too seriously when someone sounded highly confident, so I’m just flagging—this seems like a good insight but I’d guess the model as described is less general than it sounds, and I couldn’t tell you exactly how much less general off the top of my head.

But also, it’s a pattern I’ve noticed as well, and have found to be incredibly useful to be aware of. So, weak upvoted.

the gears to ascension 18 Sep 2024 10:36 UTC
14 points
0
in reply to: Lucius Bushnaq’s comment on: Lucius Bushnaq’s Shortform
I do think natural latents could have a significant role to play somehow in QACI-like setups, but it doesn’t seem like they let you avoid formalizing, at least in the way you’re talking about. It seems more interesting in terms of avoiding specifying a universal prior over possible worlds, if we can instead specify a somewhat less universal prior that bakes in assumptions about our worlds’ known causal structure. it might help with getting a robust pointer to the start of the time snippet. I don’t see how it helps avoiding specifying “looping”, or “time snippet”, etc. natural latents seem to me to be primarily about the causal structure of our universe, and it’s unclear what they even mean otherwise. it seems like our ability to talk about this concept is made up of a bunch of natural latents, and some of them are kind of messy and underspecified by the phrase, mainly relating to what the heck is a physics.

the gears to ascension 11 Sep 2024 8:32 UTC
4 points
0
in reply to: Ben Pace’s comment on: Ben Pace’s Shortform Feed
I like #2. On a similar thread: would be nice to have a separate section for pinned comments. I looked into pull requesting it at one point but looks like it either isn’t as trivial as I hoped, or I simply got lost in the code. I feel like folks having more affordance to say, “Contrary to its upvotes or recency, I think this is one of the most representative comments from me, and others seeing my page should see it” would be helpful—pinning does this already but it has ui drawbacks because it simply pushes recent comments out of the way and the pinned marker is quite small (hence why I edit my pinned comments to say they’re pinned).

the gears to ascension 31 Aug 2024 20:58 UTC
6 points
1
on: Epistemic states as a potential benign prior

then you’re not guaranteed that your AI gets anywhere at all; its knightian uncertainty might remain so immense that the AI keeps picking the null action all the time because some of its knightian hypotheses still say that anything else is a bad idea.

@Tamsin, The knightian in IB is related to limits of what hypotheses you can possibly find/write down, not—if i understand so far—about an adversary. The adversary stuff is afaict mostly to make proofs work.

@all, anyway the big issue I (still) have with this is still that, if the user is trying to give these statements, how bad is it if they screw up in some nonobvious fundamental way? Does this prior instantly collapse if the user is a kinda bad predictor on some important subset of logic or makes only statements that aren’t particularly connected to some part of the statements needed to describe reality?

I’d be particularly interested to see Garrabrant, Kosoy, Diffractor, Gurkenglas comment on where they think this works or doesn’t

the gears to ascension 30 Aug 2024 2:57 UTC
5 points
0
in reply to: Ruby’s comment on: Ruby’s Shortform Feed
Interested! I would pay at cost if that was available. I’ll be asking about which posts are relevant to a question, misc philosophy questions and asking for Claude to challenge me, etc. Primarily interested if I can ask for brevity using a custom prompt, in the system prompt.

the gears to ascension 27 Aug 2024 18:08 UTC
17 points
2
on: the gears to ascenscion’s Shortform
Wei Dai and Tsvi BT posts have convinced me I need to understand how one does philosophy significantly better. Anyone who thinks they know how to learn philosophy, I’m interested to hear your takes on how to do that. I get the sense that perhaps reading philosophy books is not the best way to learn to do philosophy.

I may edit this comment with links as I find them. Can’t reply much right now though.

the gears to ascension 20 Aug 2024 21:35 UTC
4 points
0
on: Release: Optimal Weave (P1): A Prototype Cohabitive Game
This looks really interesting, I’d be eager to try an online version if it’s not too much trouble to make?

the gears to ascension 14 Aug 2024 5:29 UTC
−17 points
−19
in reply to: habryka’s comment on: Eugenics And Reproduction Licenses FAQs
[edit 7d later: I was too angry here. I think there’s some version of this that can be defended, but it’s not the version I wrote while angry. edit 2mo latet: It’s pretty close, but my policy suggestions need refinement and I need to justify why I think the connection to past eugenics still exists.]
~~they’re welcome to argue in favor of~~ ~~genetic enhancement~~~~, as long as it happens~~ ~~after birth~~~~. yes, I know it’s orders of magnitude harder. But knowing~~ ~~anything~~ ~~about an abortable child should be illegal. I’m a big fan of abortion,~~ ~~as long as it is blind to who is being aborted,~~ because as soon as it depends on the child’s characteristics, it’s reaching into the distribution and killing some probabilistic people—without that, it’s not killing the probabilistic person. Another way to put this is, life begins at information leakage. anything else permits information leakage that imposes the agency of the parents. That’s not acceptable. Argue for augmenting a living organism all you want! we’ll need at least mild superintelligence to pull it off, unfortunately, but it’s absolutely permitted by physics. But your attempt to suppress the societal immune response to this thing in particular is unreasonable. Since you’ve already driven away the people who would say this in so many words by not banning it sooner, it is my responsibility to point this out. Almost everyone I know who I didn’t meet from lesswrong ~~hates this website,~~ ~~and they specifically cite acceptance of eugenics as why. You’re already silencing a crowd. I will not shut up.~~

the gears to ascension 14 Aug 2024 2:02 UTC
−27 points
−28
in reply to: Zero Contradictions’s comment on: Eugenics And Reproduction Licenses FAQs
[edit 7d later: I was too angry here. I think there’s some version of this that can be defended, but it’s not the version I wrote while angry. edit 2mo latet: It’s pretty close, but my policy suggestions need refinement and I need to justify why I think the connection to past eugenics still exists.]
If abortion should be “blind to the child’s attributes”, then you should put your money where you mouth is and be willing to take of disabled children who will never have a future or be able to take care of themselves. If you won’t do that, then you should concede. Your dogma will not create a sustainable, long-lasting civilization.
Solve these things in already-developed organisms. It’s orders of magnitude harder, yes, but it’s necessary for it to be morally acceptable. Your brother should get to go into cryonics and be revived once we can heal him. Failing that, it’s just the risk you take reproducing. Or at least, that will remain my perspective, since I will keep repeating, from my dad’s perspective, I would have been a defect worth eliminating. There is nothing you can say to convince me, and I will take every option available to me to prevent your success at this moral atrocity. ~~Sorry about the suffering of ancient earth, but let’s fix it in a way that produces outcomes worth creating rather than hellscapes of conformity.~~

the gears to ascension 14 Aug 2024 1:56 UTC
−29 points
−19
in reply to: habryka’s comment on: Eugenics And Reproduction Licenses FAQs
[edit 7d later: I was too angry here. I think there’s some version of this that can be defended, but it’s not the version I wrote while angry. edit 2mo latet: It’s pretty close, but my policy suggestions need refinement and I need to justify why I think the connection to past eugenics still exists.]
it kind of is, actually. Perhaps you could try not wearing your “pretense of neutrality” belief as attire and actually consider what you just said is acceptable. I’d rather say, “if something can reasonably be described as eugenics, that’s an automatic failure of acceptability, and you have to argue why your thing is ~~not~~ ~~eugenics in order for it to be welcome~~ ~~anywhere.”~~ ~~bodily autonomy means against your parents, too.~~
~~edit: i was ratelimited for this bullshit. fuck this website~~

the gears to ascension 13 Aug 2024 17:16 UTC
4 points
0
in reply to: jacquesthibs’s comment on: jacquesthibs’s Shortform
I have a user script that lets me copy the post into the Claude ui. No need to pay another service.

the gears to ascension 13 Aug 2024 17:14 UTC
−32 points
−20
in reply to: Zero Contradictions’s comment on: Eugenics And Reproduction Licenses FAQs
[edit 7d later: I was too angry here. I think there’s some version of this that can be defended, but it’s not the version I wrote while angry. edit 2mo latet: It’s pretty close, but my policy suggestions need refinement and I need to justify why I think the connection to past eugenics still exists.]

~~I sure didn’t. I’m surprised you expected to be downvoted. This shit typically gets upvoted here. My comment being angry and nonspecific will likely be in the deep negatives.~~

~~That said, I gave an argument sketch. People use this to eliminate people like me and my friends. Got a counter, or is my elevated emotion not worth taking seriously?~~

the gears to ascension 13 Aug 2024 16:58 UTC
−38 points
−39
on: Eugenics And Reproduction Licenses FAQs
[edit 7d later: I was too angry here. I think there’s some version of this that can be defended, but it’s not the version I wrote while angry. edit 2mo latet: It’s pretty close, but my policy suggestions need refinement and I need to justify why I think the connection to past eugenics still exists.]

Get this Nazi shit off this fucking website already for fuck’s sake. Yeah yeah discourse norms, I’m supposed to be nice and be specific. But actually fuck off. I’m tired of all of y’all that upvote posts like these to 100 karma. If you can’t separate your shit from eugenics then your shit is bad. Someone else can make the reasoned argument, I’ve had enough.

If we can’t get tech advanced enough to become shapeshifters, modify already grown bodies, we don’t get to mess with genes. I will never support tools that let people select children by any characteristic, they would have been used against me and so many of my friends. Wars have been fought over this, and if you try it, they will be again. Abortion should be blind to the child’s attributes.

the gears to ascension 13 Aug 2024 16:04 UTC
4 points
2
in reply to: Shankar Sivarajan’s comment on: J’s Shortform
Mmm. If someone provides real examples and gets downvoted for them, isn’t that stronger evidence of issues here? I think you are actually just wrong about this claim. Also, if you in particular provide examples of where you’ve been downvoted I expect it will be ones that carry my downvote because you were being an ass, rather than because of any factual claim they contain. (And I expect to get downvoted for saying so!)

j is likely to not have that problem, unless they also are systematically simply being an ass and calling it an opinion. If you describe ideas and don’t do this shit Shankar and I are, I think you probably won’t be downvoted.