the gears to ascension

Karma: 5,131

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 12 Dec 2024 20:46 UTC
4 points
0
in reply to: Nathan Helm-Burger’s comment on: the gears to ascenscion’s Shortform

I don’t think the answer is as simple as changing terminology or carefully modelling their current viewpoints and bridging the inferential divides.

Indeed, and I think that-this-is-the-case is the message I want communicators to grasp: I have very little reach, but I have significant experience talking to people like this, and I want to transfer some of the knowledge from that experience to people who can use it better.

The thing I’ve found most useful is to be able to express that significant parts of their viewpoint are reasonable. Eg, one thing I’ve tried is “AI isn’t just stealing our work, it’s also stealing our competence”. Hasn’t stuck, though. I find it helpful to point out that yes, climate change sure is a (somewhat understated) accurate description of what doom looks like.

I do think “allergies” are a good way to think about it, though. They’re not unable to consider what might happen if AI keeps going as it is, they’re part of a culture that is trying to apply antibodies to AI. And those antibodies include active inference wishcasting like “AI is useless”. They know it’s not completely useless, but the antibody requires them to not acknowledge that in order for its effect to bind; and their criticisms aren’t wrong, just incomplete—the problems they raise with AI are typically real problems, but not high impact ones so much as ones they think will reduce the marketability of AI.
What links here?
- the gears to ascension's comment on [Fiction] A Disneyland Without Children by L Rudolf L (12 Dec 2024 20:44 UTC; 6 points)

the gears to ascension 12 Dec 2024 20:44 UTC
6 points
0
on: [Fiction] A Disneyland Without Children
This is the story I use to express what a world where we fail looks like to left-leaning people who are allergic to the idea that AI could be powerful. It doesn’t get the point across great, due to a number of things that continue to be fnords for left leaning folks which this story uses, but it works better than most other options. It also doesn’t seem too far off what I expect to be the default failure case; though the factories being made of low-intelligence robotic operators seems unrealistic to me.

I opened it now to make this exact point.

the gears to ascension 11 Dec 2024 16:14 UTC
2 points
0
in reply to: Viliam’s comment on: sarahconstantin’s Shortform
This is talking about dem voters or generally progressive citizens, not dem politicians, correct?

the gears to ascension 11 Dec 2024 7:13 UTC
22 points
5
on: the gears to ascenscion’s Shortform
people who dislike AI, and therefore could be taking risks from AI seriously, are instead having reactions like this. https://blue.mackuba.eu/skythread/?author=brooklynmarie.bsky.social&post=3lcywmwr7b22i why? if we soberly evaluate what this person has said about AI, and just, like, think about why they would say such a thing—well, what do they seem to mean? they typically say “AI is destroying the world”, someone said that in the comments; but then roll their eyes at the idea that AI is powerful. They say the issue is water consumption—why would someone repeat that idea? Under what framework is that a sensible combination of things to say? what consensus are they trying to build? what about the article are they responding to?

I think there are straightforward answers to these questions that are reasonable and good on behalf of the people who say these things, but are not as effective by their own standards as they could be, and which miss upcoming concerns. I could say more about what I think, but I’d rather post this as leading questions, because I think the reading of the person’s posts you’d need to do to go from the questions I just asked to my opinions will build more of the model I want to convey than saying it directly.

But I think the fact that articles like this get reactions like this is an indication that orgs like Anthropic or PauseAI are not engaging seriously with detractors, and trying seriously to do so seems to me like a good idea. It’s not my top priority ask for Anthropic, but it’s not very far down the virtual list.

But it’s just one of many reactions of this category I’ve seen that seem to me to indicate that people engaging with a rationalist-type negative attitude towards their observations of AI are not communicating successfully with people who have an ordinary-person-type negative attitude towards what they’ve seen of AI. I suspect that at least a large part of the issue is that rationalists have built up antibodies to a certain kind of attitude and auto-ignore it, despite what I perceive to be its popularity, and as a result don’t build intuitive models about how to communicate with such a person.

the gears to ascension 8 Dec 2024 18:40 UTC
7 points
0
in reply to: habryka’s comment on: Habryka’s Shortform Feed
I suspect fixing this would need to involve creating something new which doesn’t have the structural problems in EA which produced this, and would involve talking to people who are non-sensationalist EA detractors but who are involved with similarly motivated projects. I’d start here and skip past the ones that are arguing “EA good” to find the ones that are “EA bad, because [list of reasons ea principles are good, and implication that EA is bad because it fails at its stated principles]”

I suspect, even without seeking that out, the spirit of EA that made it ever partly good has already and will further metastasize into genpop.

the gears to ascension 8 Dec 2024 18:30 UTC
4 points
0
in reply to: leogao’s comment on: leogao’s Shortform
I was someone who had shorter timelines. At this point, most of the concrete part of what I expected has happened, but the “actually AGI” thing hasn’t. I’m not sure how long the tail will turn out to be. I only say this to get it on record.

the gears to ascension 8 Dec 2024 12:20 UTC
4 points
0
in reply to: Gunnar_Zarncke’s comment on: Optimizing for Agency?
https://www.drmichaellevin.org/research/

https://www.drmichaellevin.org/publications/

it’s not directly on alignment, but it’s relevant to understanding agent membranes. understanding his work seems useful as a strong exemplar of what one needs to describe with a formal theory of agents and such. particularly interesting is https://pubmed.ncbi.nlm.nih.gov/31920779/

It’s not the result we’re looking for, but it’s inspiring in useful ways.

the gears to ascension 6 Dec 2024 21:04 UTC
4 points
0
in reply to: Gunnar_Zarncke’s comment on: Optimizing for Agency?
Yes to both. I don’t think Cannell is correct about an implementation of what he said being a good idea, even if it was a certified implementation, and I also don’t think his idea is close to ready to implement. Agent membranes still seem at all interesting, right now as far as I know the most interesting work is coming from the Levin lab (tufts university, michael levin), but I’m not happy with any of it for nailing down what we mean by aligning an arbitrarily powerful mind to care about the actual beings in its environment in a strongly durable way.

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: Aidan Mokalla’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
32 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.