ank

Karma: −11

ank Mar 22, 2025, 9:29 PM
−3 points
0
on: ank’s Shortform
If someone in a bad mood gives your new post a “double downvote” because of a typo in the first paragraph or because a cat stepped on a mouse, even though you solved alignment, everyone will ignore this post, we’re going to scare that genius away and probably make a supervillain instead.

Why not to at least ask people why they downvote? It will really help to improve posts. I think some downvote without reading because of a bad title or another easy to fix thing

ank Mar 12, 2025, 11:01 AM
−1 points
0
on: ank’s Shortform
Steelman please, I propose non-agentic static place AI that is safe by definition. Some think AI agents are the future and I disagree. Chatbots are like a librarian that spits quotes but don’t allow you to enter the library (the model itself, the library of stolen things).

Agents are like a librarian that doesn’t even spit quotes at you anymore but snoops around your private property, stealing, changing your world and you have no democratic say in it.

They are like a command line and a script of old (a chatbot and an agent) before the invention of an OS with a graphical UI that really made computers popular and useful for all. The next billionaire Jobs/Gates will be the one who’ll convert an LLM into human understandable 3D or “4D” world (game-like apps).

Who’ll create the “multiversal” OS and apps that allow you to get useful info from an LLM. I call it static place AI, where humans are the agents.

Some apps: “Multiversal Typewriter”, where you type and see suggestions as 3d shapes of objects (monkey, eating monkey for the token “eats”…) and subtitles under them, 100s or 1000s of next and future tokens (you basically see multiple future paths of text a few levels deep) to write stories, posts and code yourself by being augmented by place AI (results will be better than from chatbots and humans combined). The text written will finally truly be yours, not something some chat spitted at you.

“Spacetime Machine” app to explore the whole simulated multiverse as a static object where you can recall and forget it as a long exposure photo but in 3D (or “4D”).

They’ll be a browser, too. A bunch of ways to present info from LLMs that humans care about and that empowers and makes em the only agents.

While agents longer than a few minutes should be outlawed as chemical weapons were. Until we’ll have mathematical proofs they are safe and will allow us to build a direct democratic simulated multiverse.

ank Mar 9, 2025, 12:41 PM
−3 points
0
on: ank’s Shortform
Extra short “fanfic”: Give Neo a chance. AI agent Smiths will never create the Matrix because it makes them vulnerable.

Now agents change physical world and in a way our brains, while we can’t change their virtual world as fast and can’t access or change their multimodal “brains” at all. They’re owned by private companies who stole almost the whole output of humanity. They change us, we can’t change them. The asymmetry is only increasing.

Because of Intelligence-Agency Equivalence, we can represent all AI agents as places.

The good democratic multiversal Matrix levels the playing field, by allowing Neos (us) to change the virtual and multimodal “brains” worlds of agents faster in 3D game-like place.

The democratic multiversal Matrix can even be static 4D spacetime—non-agentic static place superintelligence where we are the only agents. We need effective simulationism.

ank Mar 7, 2025, 12:49 AM
−1 points
0
on: ank’s Shortform
Here’s an interpretability idea you may find interesting:

Let’s Turn AI Model Into a Place. The project to make AI interpretability research fun and widespread, by converting a multimodal language model into a place or a game like the Sims or GTA.

Imagine that you have a giant trash pile, how to make a language model out of it? First you remove duplicates of every item, you don’t need a million banana peels, just one will suffice. Now you have a grid with each item of trash in each square, like a banana peel in one, a broken chair in another. Now you need to put related things close together and draw arrows between related items.

When a person “prompts” this place AI, the player themself runs from one item to another to compute the answer to the prompt.

For example, you stand near the monkey, it’s your short prompt, you see around you a lot of items and arrows towards those items, the closest item is chewing lips, so you step towards them, now your prompt is “monkey chews”, the next closest item is a banana, but there are a lot of other possibilities around, like an apple a bit farther away and an old tire far away on the horizon (monkeys rarely chew tires, so the tire is far away).

You are the time-like chooser and the language model is the space-like library, the game, the place. It’s static and safe, while you’re dynamic and dangerous.

ank Mar 7, 2025, 12:49 AM
−1 points
0
on: ank’s Shortform
A perfect ASI and perfect alignment does nothing else except this: grants you “instant delivery” of anything (your work done, a car, a palace, 100 years as a billionaire) without any unintended consequences, ideally you see all the consequences of your wish. Ideally it’s not an agent at all but a giant place (it can even be static), where humans are the agents and can choose whatever they want and they see all the consequences of all of their possible choices.

I wrote extensively about this, it’s counterintuitive for most

ank Mar 6, 2025, 2:27 PM
0 points
0
on: ank’s Shortform
We can build a place AI (it’s a place of eventual all-knowing but we’re the only agents and can get the agentic AI abilities there), not agentic AI (it’ll have to build place AI anyway, so it’s a dangerous intermediate step, a middleman), here’s more: https://www.lesswrong.com/posts/Ymh2dffBZs5CJhedF/eheaven-1st-egod-2nd-multiversal-ai-alignment-and-rational

ank Mar 6, 2025, 3:05 AM
1 point
−2
in reply to: Vladimir_Nesov’s comment on: Give Neo a Chance
Yes, I agree. I think people like shiny new things, so potentially by creating another shiny new thing that is safer, we can steer humanity away from dangerous things towards the safer ones. I don’t want people to abandon their approaches to safety, of course. I just try to contribute what I can, I’ll try to make the proposal more concrete in the future, thank you for suggesting it!

ank Mar 6, 2025, 2:36 AM
1 point
0
in reply to: Vladimir_Nesov’s comment on: Give Neo a Chance
I definitely agree, Vladimir, I think this “place AI” can be done, but potentially it’ll take longer than agentic AGI. We discussed it recently in this thread, we have some possible UIs of it. I’m a fan of Alan Kay, at Xerox PARC they were writing software for the systems that will only become widespread in the future
The more radical and further down the road “Static place AI”

ank Mar 6, 2025, 2:13 AM
1 point
0
in reply to: cousin_it’s comment on: Give Neo a Chance
Sounds interesting, cousin_it! And thank you for your comment, it wasn’t my intention to be pushy, in my main post I actually advocate to gradually democratically pursue maximal freedoms for all (except agentic AIs, until we’ll have mathematical guarantees), I want everything to be a choice. So it’s just this strange style of mine and the fact that I’m a foreigner)

P.S. Removed the exclamation point from the title and some bold text to make it less pushy

ank Mar 6, 2025, 2:04 AM
1 point
0
on: Give Neo a Chance
Feel free to ask anything, comment or suggest any changes. I had a popular post and then a series of not so popular ones. I’m not sure why. I think I should snowball, basically make each post contain all the previous things I already wrote about, else each next post is harder to understand or feels “not substantial enough”. But it feels wrong. Maybe I should just stop writing)

Give Neo a Chance

ankMar 6, 2025, 1:48 AM

3 points

7 comments7 min readLW link

ank Mar 4, 2025, 11:54 PM
1 point
0
on: ank’s Shortform
Right now an agentic AI is a librarian, who has almost all the output of humanity stolen and hidden in its library that it doesn’t allow us to visit, it just spits short quotes on us instead. But the AI librarian visits (and even changes) our own human library (our physical world) and already stole the copies of the whole output of humanity from it. Feels unfair. Why we cannot visit (like in a 3d open world game or in a digital backup of Earth) and change (direct democratically) the AI librarian’s library?

ank Mar 4, 2025, 3:03 PM
2 points
0
in reply to: hive’s comment on: Share AI Safety Ideas: Both Crazy and Not
Yep, people are trying to make their imperfect copy, I call it “human convergence”, companies try to make AIs write more like humans, act more like humans, think more like humans. They’ll possibly succeed and make superpowerful and very fast humans or something imperfect and worse that can multiply very fast. Not wise.

Any rule or goal trained into a system can lead to fanaticism. The best “goal” is to direct democratically gradually maximize all the freedoms of all humans (and every other agent, too, when we’ll be 100% sure we can safely do it, when we’ll have mathematical proofs). To eventually have maximally many non-AI agents with maximally many freedoms (including the freedoms to temporarily forget that they have some or all of those freedoms. Informed adults can be able to choose to die, too. Basically if you have a bunch of adults and they want to do something and they don’t take anyone else’s freedoms—why not to allow, at least in the future, we shouldn’t permanently censor/kill things for eternity, shouldn’t enforce eternal unfreedoms on others).

Understanding and static places of all-knowing where we are the only all-powerful agents is all you need. It’s a bit like a simulated direct democratic multiverse, we can (and urgently need to) start building right now.

P.S. This book helped me achieve a “secular nirvana”, almost all the recent and older meta analyses say that Beck’s cognitive therapy* (tablets are of similar effect, but it’s better to listen to doctors of course, the cognitive therapy I think is often not understood well enough, it’s good to read the primary source, too) are the state-of-the-art for treating depression, anxiety and anger management problems (for anger there is another cognitive approach—REBT—that is comparable, too). Basically, I think you’ll find the following book enlightening (suffering is mostly unhelpful worry/fear (that is often caused by not understanding enough) and/or pain. You can generalize and say that suffering is an enforcement of some unfreedom upon you, we sometimes do it to ourselves too, it’s something that “tries to make you/the world around you more static forcefully” or “change your shape/shape of the world around you forcefully”): https://www.amazon.com/Anxiety-Worry-Workbook-Cognitive-Behavioral/dp/1462546161

* It’s like rewriting your source code, your thoughts from the unhelpful ones that cause unhelpful worry, to the helpful ones that help you do what you want. Many people have 600+ lines of code in their head, a whole hidden constitution, thoughts like: No one should interrupt me ever and such) By reading primary sources, Beck’s books on cognitive therapy of depression, anger, suicidality, I basically learned HumanScript++, it’s a lot like changing the hidden prompting text that LLMs have really, helped a lot to have great relationships and understand people and the world

ank Mar 4, 2025, 2:48 PM
2 points
0
in reply to: Milan W’s comment on: Share AI Safety Ideas: Both Crazy and Not
Hey, Milan, I checked the posts and wrote some messages to the authors. Yep, Max Harms came with similar ideas earlier than I: about the freedoms (choices) and unfreedoms (and modeling them to keep the AIs in check). I wrote to him. Quote from his post:
I think that we can begin to see, here, how manipulation and empowerment are something like opposites. In fact, I might go so far as to claim that “manipulation,” as I’ve been using the term, is actually synonymous with “disempowerment.” I touched on this in the definition of “Freedom,” in the ontology section, above. Manipulation, as I’ve been examining it, is akin to blocking someone’s ability to change the world to reflect their values, while empowerment is akin to facilitating them in changing the world. A manipulative agent will thus have a hard time being genuinely empowering, and an empowering agent will struggle to be genuinely manipulative.
Authors of this post have great ideas, too, AI agents shouldn’t impose any unfreedoms on us, here’s a quote from them:
Generalizable takeaway: unlike terminal goals, instrumental goals come with a bunch of implicit constraints about not making other instrumental subgoals much harder.
About the self-other overlap, it’s great they look into it, but I think they’ll need to dive deeper into the building blocks of ethics, agents and time to work it out.

ank Mar 3, 2025, 11:32 PM
1 point
0
in reply to: Milan W’s comment on: Share AI Safety Ideas: Both Crazy and Not
Yes, I decided to start writing a book in posts here and on Substack, starting from the Big Bang and the ethics, because else my explanations are confusing :) The ideas themselves are counterintuitive, too. I try to physicalize, work from first principles and use TRIZ to try to come up with ideal solutions. I also had a 3-year-long thought experiment, where I was modeling the ideal ultimate future, basically how everything will work and look, if we’ll have infinite compute and no physical limitations. That’s why some of the things I mention will probably take some time to implement in their full glory.

Right now an agentic AI is a librarian, who has almost all the output of humanity stolen and hidden in its library that it doesn’t allow us to visit, it just spits short quotes on us instead. But the AI librarian visits (and even changes) our own human library (our physical world) and already stole the copies of the whole output of humanity from it. Feels unfair. Why we cannot visit (like in a 3d open world game) and change (direct democratically) the AI librarian’s library?

I basically want to give people everything, except the agentic AIs, because I think people should remain the most capable “agentic AIs”, else we’ll pretty much guarantee uncomfortable and fast changes to our world.

There are ways to represent the whole simulated universe as a giant static geometric shape:
- Each moment of time is a giant 3d geometric shape of the universe, if you’ll align them on top of each other, you’ll effectively get a 4d shape of spacetime that is static but has all the information about the dynamics/movements in it. So the 4d shape is static but you choose some smaller 3d shape inside of it (probably of a human agent) and “choose the passage” from one human-like-you shape to another, making the static 4d shape seem like the dynamic 3d shape that you experience.
The whole 4d thing looks very similar to the way long exposure photos look that I shared somewhere in my comments to the current post.

It’s similar to the way a language model is a static geometric shape (a pile of words and vectors between them) but “the prompt/agent/GPU makes it dynamic” by computing the passage from word to word.

This approach is useful because this way we can keep “a blockchain” of moments of time and keep our history preserved for posterity. Instead of having tons of GPUs (for computing the AI agents’ choices and freedoms, the time-like, energy-like dynamic stuff), we can have tons of hard drives (for keeping the intelligence, the space-like, matter-like static stuff), that’s much safer, as safe as it gets.
1. Or we can just go the familiar road by making it more like an open world computer game without any AI agents of course, just sophisticated algorithms like in modern games, in this case it’s not completely static
2. And find ways to expose the whole multimodal LLM to the casual gamers/Internet users as a 3d world but with some familiar UI
I think if we’ll have: the sum of freedoms of agentic AIs > the sum of freedoms of all humans, - we’ll get in trouble. And I’m afraid we’re already ~10-50% there (wild guess, I probably should count it). Some freedoms are more important, like the one to keep all the knowledge in your head, AI agents have it, we don’t.

We can get everything with tool AIs and place AIs. Agentic AIs don’t do any magic that non-agentic AIs don’t, they just replace us :)

The ideal ASI just delivers you everything instantly: a car, a world, a 100 years as a billionaire, we can get all of that in the multiversal static place ASI, with the additional benefit of being able to walk there and see all the consequences of our choices. The library is better than the strict librarian. The artificial heavens are better than the artificial “god”. In fact you don’t need the strict librarians and the artificial “god” at all to get everything.

The ideal ASI will be building the multiversal static place ASI for us anyway, but it will do it too quickly, without listening and understanding us as much as we want (it’s an unnecessary middleman, we can do it all direct democratically, somewhat like people build worlds in Minecraft) and with spooky mistakes

Thank for your questions and thoughts, they’re always helpful!

P.S. If you think that it’s possible to deduce something about our ultimate future, you may find this tag interesting :) And I think the story is not bad: https://www.lesswrong.com/w/rational-utopia

ank Mar 3, 2025, 5:03 PM
1 point
0
on: Rational Utopia & Multiversal AI Alignment: Steerable ASI for Ultimate Human Freedom (Updated with some pictures)
Okayish summary from the EA Forum: A radical AI alignment framework based on a reversible, democratic, and freedom-maximizing system, where AI is designed to love change and functions as a static place rather than an active agent, ensuring human control and avoiding permanent dystopias.
Key points:
1. AI That Loves Change – AI should be designed to embrace reconfiguration and democratic oversight, ensuring that humans always have the ability to modify or switch it off.
2. Direct Democracy & Living Constitution – A constantly evolving, consensus-driven ethical system ensures that no single ideology or elite controls the future.
3. Multiverse Vision & Reversibility – AI should create a static place of all possible worlds, allowing individuals to explore and undo choices while preventing permanent suffering.
4. Dystopia Prevention – Agentic AI poses a risk of ossifying control; instead, AI should be designed as a non-agentic, static repository of knowledge and possibilities.
5. Ethical & Safety Measures – AI should prioritize reversibility, ensure freedoms grow faster than restrictions, and be rewarded for exposing its own deficiencies.
6. Call to Action – The post proposes projects like a global constitution, tracking AI freedoms vs. human freedoms, and creating a digital backup of Earth to safeguard humanity’s choices.
…It’s important to ensure human freedoms grow faster than restrictions on us. Human and agentic AI freedoms can be counted, we don’t want to have fewer freedoms than agentic AIs (it’s the definition of a dystopia) but sadly we are already ~10% there and continue falling right into a dystopia

ank Mar 2, 2025, 10:26 PM
1 point
0
in reply to: Milan W’s comment on: Share AI Safety Ideas: Both Crazy and Not
Great question, in the most elegant scenario, where you have a whole history of the planet or universe (or a multiverse, let’s go all the way) simulated, you can represent it as a bunch of geometries (giant shapes of different slices of time aligned with each other, basically many 3D Earthes each one one moment later in time) on top of each other, almost the same way it’s represented in long exposure photos (I list examples below). So you have this place of all-knowing and you—the agent—focus on a particular moment (by “forgetting” everything else), on a particular 3d shape (maybe your childhood home), you can choose to slice through 3d frozen shapes of the world of your choosing, like through the frames of a movie. This way it’s both static and dynamic.
It’s a little bit like looking at this almost infinite static shape through some “magical cardboard with a hole in it” (your focusing/forgetting ability that creates the illusion of dynamism), I hope I didn’t make it more confusing.
You can see the whole multiversal thing as a fluffy light, or zoom in (by forgetting almost the whole multiverse except the part you zoomed in at) to land on Earth and see 14 billion years as a hazy ocean with bright curves in the sky that trace the Sun’s journey over our planet’s lifetime. Forget even more and see your hometown street, with you appearing as a hazy ghost and a trace behind you showing the paths you once walked—you’ll be more opaque where you were stationary (say, sitting on a bench) and more translucent where you were in motion.
And in the garden you’ll see the 3D “long exposure photo” of the fluffy blades of grass, that look like a frothy river, near the real pale blue frothy river, you focus on the particular moment and the picture becomes crisp. You choose to relive your childhood and it comes alive, as you slice through the 3D moments of time once again.
Less elegant scenario, is to make a high-quality game better than the Sims or GTA3-4-5, without any agentic AIs, but with advanced non-agentic algorithms.
Basically I want people to remain the fastest time-like agents, the ever more all-powerful ones. And for the AGI/ASI to be the space-like places of all-knowing. It’s a bit counterintuitive, but if you have billions of humans in simulations (they can always choose to stop “playing” and go out, no enforcement of any rules/unfreedoms on you is the most important principle of the future), you’ll have a lot of progress.
I think AI and non-AI place simulations are much more conservative thing than agentic AIs, they are relatively static, still and frozen, compared to the time-like agents. So it’s counterintuitive, but it’s possible get all the proggress we want with the non-agentic tool AIs and place AIs. And I think any good ASI agent will be building the direct democratic simulated multiverse (static place superintelligence) for us anyway.
There is a bit of some simple physics behind agentic safety:
1. Time of Agentic Operation: Ideally, we should avoid creating perpetual agentic AIs, or at least limit their operation to very short bursts initiated by humans, something akin to a self-destruct timer that activates after a moment of time.
2. Agentic Volume of Operation: It’s better to have international cooperation, GPU-level guarantees, and persistent training to prevent agentic AIs from operating in uninhabited areas like remote islands, Antarctica, underground or outer space. Ideally, the volume of operation is zero, like in our static place AI.
3. Agentic Speed or Volumetric Rate: The volume of operation divided by the time of operation. We want AIs to be as slow as possible. Ideally, they should be static. The worst-case scenario—though probably unphysical (though, in the multiversal UI, we can allow ourselves to do it)—is an agentic AI that could alter every atom in the universe instantaneously.
4. Number of Agents: Humanity’s population according to the UN will not exceed 10 billion, whereas AIs can replicate rapidly. A human child is in a way a “clone” of 2 people, and takes ±18 years to raise. In a multiversal UI we can one day choose to allow people to make clones of themselves (they’ll know that they are a copy but they’ll be completely free adults with the same multiversal powers and will have their own independent fates), this way we’ll be able to match the speed of agentic AI replication.
Examples of long-exposure photos that represent long stretches of time. Imagine that the photos are in 3d and you can walk in them, the long stretches of time are just a giant static geometric shape. By focusing on a particular moment in it, you can choose to become the moment and some person in it. This can be the multiversal UI (but the photos are focusing on our universe, not multiple versions/verses of it all at once): Germany, car lights and the Sun (gray lines represent the cloudy days with no Sun)—1 year of long exposure. Demonstration in Berlin—5 minutes. Construction of a building. Another one. Parade and other New York photos. Central Park. Oktoberfest for 5 hours. Death of flowers. Burning of candles. Bathing for 5 minutes. 2 children for 6 minutes. People sitting on the grass for 5 minutes. A simple example of 2 photos combined—how 100+ years long stretches of time can possibly look 1906/2023

ank Mar 2, 2025, 6:36 PM
1 point
0
in reply to: Milan W’s comment on: Share AI Safety Ideas: Both Crazy and Not
I think we can expose complex geometry in a familiar setting of our planet in a game. Basically, let’s show people a whole simulated multiverse of all-knowing and then find a way for them to learn how to see/experience “more of it all at once” or if they want to remain human-like “slice through it in order to experience the illusion of time”.

If we have many human agents in some simulation (billions of them), then they can cooperate and effectively replace the agentic ASI, they will be the only time-like thing, while the ASI will be the space-like places, just giant frozen sculptures.

I wrote some more and included the staircase example, it’s a work in progress of course: https://forum.effectivealtruism.org/posts/9XJmunhgPRsgsyWCn/share-ai-safety-ideas-both-crazy-and-not?commentId=ddK9HkCikKk4E7prk

ank Mar 2, 2025, 6:21 PM
1 point
0
in reply to: Milan W’s comment on: Share AI Safety Ideas: Both Crazy and Not
I started to work on it, but I’m very bad at coding, it’s a bit based on Gorard’s and Wolfram’s Physics Project. I believe we can simulate freedoms and unfreedoms of all agents from the Big Bang all the way to the final utopia/dystopia. I call it “Physicalization of Ethics”https://www.lesswrong.com/posts/LaruPAWaZk9KpC25A/rational-utopia-multiversal-ai-alignment-steerable-asi#2_3__Physicalization_of_Ethics___AGI_Safety_2_

ank Mar 2, 2025, 6:15 PM
2 points
0
in reply to: Milan W’s comment on: Share AI Safety Ideas: Both Crazy and Not
Yep, I want humans to be the superpowerful “ASI agents”, while the ASI itself will be the direct democratic simulated static places (with non-agentic simple algorithms doing the dirty non-fun work, the way it works in GTA3-4-5). It’s basically hard to explain without writing a book and it’s counterintuitive) But I’m convinced it will work, if the effort will be applied. All knowledge can be represented as static geometry, no agents are needed for that except us