ank — LessWrong

LESSWRONG
LW

ank — LessWrong

“It is probably a lot more efficient to show that by modifying the LAION database and slapping some sort of image search on it, so people can see that their pictures were used to train the model.”

Sounds great, bohaska! Yes, it should be possible to have an image search so people can find their personal photos or their faces (or something very similar to their faces). The art gallery idea just makes it more appealing to YouTubers and millions of viewers, they like haunted houses in 3D.

Wolfram mentioned “bridges between concepts”: you can have a picture of a human face that morphs into a dog. Crazy stuff like that will potentially make... (read more)

Yes, bohaska, valid points, it can be a direction towards a solution. The simplest steps to get closer:

Update OSes and GPU firmwares with Anti-bad-AI "antivirus": even the simplest blacklists, heuristics and whitelists can be a start to at least prevent some novice hacker from easily spreading some unmodified AI model or agent from computer to computer. Right now we have almost 0% GPU security from an AI botnet, we want to get as close to 100% as we can. The perfect shouldn't be the enemy of the good.
Like Wolfram present a diffusion model as a world of concepts. But remove the noise, make the generated concepts like pictures in an art galley

... (read more)

ank11mo

Yes, we may want to have the ability to have some agency (especially human-initiated for less than an hour. so a person can supervise) but probably not letting agents roam free for days, weeks, years unsupervised, no one will monitor them, people cannot monitor for so long. So we better to have some limits and tools to impose those limits in every GPU

ank11mo

Thank you for your analysis, Winston! Sadly I have to write fast here because many of my posts get not much attention or minuses)

Here is a drafty continuation you can find interesting (or not ;):

In unreasonable times the solution to AI problem will sounds unreasonable at first. Even though it's probably the only reasonable and working solution.

Imagine in a year we solved alignment and even hackers/rogue states cannot unleash AI agents on us. How we did it?

The most radical solution that will do it (unrealistic and undesirable): is having international cooperation and destroying all the GPUs, never making them again. Basically returning to some 1990s computer-wise, no 3D video games but everything

... (read 581 more words →)

ank11mo

Yes, Buck, thank you for responding! A robust whitelist (especially hardware level, each GPU can become a computer for securing itself) potentially solves it (of course if there will be some state-level actors, it can potentially be broken, but at least millions of consumer GPUs will be protected). Each GPU is a battleground, we want to increase current 0% security, to above 0 on as many GPUs as possible, first in firmware (and on OS level) because updating online is easy, then in hardware (can bring much better security).

In the safest possible implementation, I imagine it as Apple App Store (or Nintendo online game shop): the AI models become a bit like... (read more)

ank11moQuick Take

The only complete and comprehensive solution that can make AIs 100% safe: in a nutshell we need to at least lobby politicians to make GPU manufacturers (NVIDIA and others) to make robust blacklists (whitelists and new non-agentic hardware, please, read on) of bad AI models, update GPU firmwares with them. It's not the full solution: please steelman and read the rest to learn how to make it much safer and why it will work (NVIDIA and other GPU makers will want to do it because it'll double their business and all future cash flows. Gov will want it because it removes all AI threats from China, all hackers, terrorists and rogue states):

... (read more)

-2

-11

Replying toShare AI Safety Ideas: Both Crazy and Not. №2

ank11mo*

Share AI Safety Ideas: Both Crazy and Not. №2

UI proposal to solve your concern that it’ll be harder to downvote (that will actually increase signal to noise ratio on the site because both authors and readers will have information why the post had downvotes) and the problem of demotivating authors:

UI proposal to solve the problem of demotivating writers, helps to teach writers how to improve their posts (so it makes all the posts better), it keeps the downvote buttons, increases signal to noise ratio on the site because both authors and readers will have information why the post was downvoted:
It’s important to ask for reasons why a downvoter downvotes if the downvote will move the post below zero in karma.

... (read 485 more words →)

Replying toShare AI Safety Ideas: Both Crazy and Not. №2

ank11mo*

Share AI Safety Ideas: Both Crazy and Not. №2

It’s a combination of factors, I got some comments on my posts so I got the general idea:

My writing style is peculiar, I’m not a native speaker
Ideas I convey took 3 years of modeling. I basically Xerox PARCed (attempted and got some results) the ultimate future (billions of years from now). So when I write it’s like some Big Bang: ideas flow in all directions and I never have enough space for them)
One commenter recommended to change the title and remove some tags, I did it
If I use ChatGPT to organize my writing it removes and garbles it. If I edit it, I like having parenthesis within parenthesis
I write a book to

ank11mo*

Share AI Safety Ideas: Both Crazy and Not. №2

Some more thoughts:

We can prevent people from double downvoting if they opened the post and instantly double downvoted (spend almost zero time on the page). Those are most likely the ones who didn’t read anything except the title.
Maybe it’s better for them to flag it instead if it was some spam or another violation, or ask to change the title. It’s unfair for the writer and other readers to get authors double downvoted just because of the bad title or some typo.
We have the ability to comment and downvote paragraphs. This feature is great. Maybe we can aggregate those and they’ll be more precise.
Especially going below zero is demotivating. So maybe we

ank

11mo

AI safety is one of the most critical issues of our time, and sometimes the most innovative ideas come from unorthodox or even "crazy" thinking. I’d love to hear bold, unconventional, half-baked or well-developed ideas for improving AI safety. You can also share ideas you heard from others.

Let’s throw out all the ideas—big and small—and see where we can take them together.

Feel free to share as many as you want! No idea is too wild, and this could be a great opportunity for collaborative development. We might just find the next breakthrough by exploring ideas we’ve been hesitant to share.

A quick request: Let’s keep this space constructive—downvote only if there’s clear trolling or spam, and be supportive of half-baked ideas. The goal is to unlock creativity, not judge premature thoughts.

Looking forward to hearing your thoughts and ideas!

P.S. The AIs are moving fast, the last similar discussion was a month ago and was well received, so let's try again and see how the ideas changed.

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

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... (read more)

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.

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... (read more)

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

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

Give Neo a Chance

ank

(To learn more about Place AI and other things mentioned here, refer to the first post in the series. Sorry for the rough edges—I’m a newcomer, non‑native speaker, and my ideas might sound strange, please steelman them and share your thoughts. The safe future is counterintuitive and takes a book to explain. My sole goal is to decrease the probability of a permanent dystopia. New technologies should be a choice, not an enforcement upon us.)

Forget the movies for a moment, imagine the following (I didn't watch the movies for a long time and we're not following the canon):

Neo is an average human living in our physical world. He has no superpowers, no

... (read 1927 more words →)

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?

Replying toShare AI Safety Ideas: Both Crazy and Not

ank1y*

Share AI Safety Ideas: Both Crazy and Not

Yes, 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

Share AI Safety Ideas: Both Crazy and Not

ank

Let’s throw out all the ideas—big and small—and see where we can take them together.

Looking forward to hearing your thoughts and ideas!

We can build the Artificial Static Place Intelligence – instead of creating AI/AGI agents that are like librarians who only give you quotes from books and don’t let you enter the library itself to read the whole books. Why not expose the whole library – the entire multimodal language model – to real people, for example, in a computer game?

To make this place easier to visit and explore, we could make a digital copy of our planet Earth and somehow expose the contents of the multimodal language model to everyone in a familiar, user-friendly UI of our planet.

We should not keep it hidden behind the strict librarian (AI/AGI agent) that imposes rules... (read more)

Unaligned AGI & Brief History of Inequality

ank

(The downvotes, as mentioned in the comments, were in large part caused by a misunderstanding, sadly people do sometimes downvote without reading, even though some articles can prevent a dystopia. This is the result of three years of thinking and modeling hyper‑futuristic and current ethical systems. It's not the first post in the series, it’s counterintuitive and can be dismissed prematurely without reading at least the first one. Everything described here can be modeled mathematically—it’s essentially geometry. I take as an axiom that every agent in the multiverse experiences real pain and pleasure. Sorry for the rough edges—I’m a newcomer, non‑native speaker, and my ideas might sound strange, so please steelman them... (read 1934 more words →)

-20

Intelligence–Agency Equivalence ≈ Mass–Energy Equivalence: On Static Nature of Intelligence & Physicalization of Ethics

ank

Imagine a place that grants any wish, but there is no catch, it shows you all the outcomes, too.

(This is the result of three years of thinking and modeling hyper‑futuristic and current ethical systems. It's not the first post in the series, it'll be very confusing and probably understood wrong without reading at least the first one. Everything described here can be modeled mathematically—it’s essentially geometry. I take as an axiom that every agent in the multiverse experiences real pain and pleasure. Sorry for the rough edges—I’m a newcomer, non‑native speaker, and my ideas might sound strange, so please steelman them and share your thoughts. My sole goal is to decrease the... (read 1506 more words →)

Places of Loving Grace [Story]

ank

(This is the result of three years of thinking and modeling hyper‑futuristic and current ethical systems. It's not the first post in the series, it can be confusing and probably understood wrong without reading at least the first one. Sorry for the rough edges—I’m a newcomer, non‑native speaker, and my ideas might sound strange, so please steelman them and share your thoughts. My sole goal is to decrease the probability of a permanent dystopia.)

-1

Places of Loving Grace

On the manicured lawn of the White House, where every blade of grass bent in flawless symmetry and the air hummed with the scent of lilacs, history unfolded beneath a sky so blue it seemed painted. The president, his golden hair glinting like a crown, stepped forward to greet the first alien ever to visit Earth—a being of cerulean grace, her limbs angelic, eyes of liquid starlight. She had arrived not in a warship, but in a vessel resembling a cloud, iridescent and silent.

Published the full story as a post here: https://www.lesswrong.com/posts/jyNc8gY2dDb2FnrFB/places-of-loving-grace

Artificial Static Place Intelligence: Guaranteed Alignment

ank

Static Place AI Makes Agentic AI Redundant: Multiversal AI Alignment & Rational Utopia

ank

(This is the result of three years of thinking and modeling hyper‑futuristic and current ethical systems. It's not the first post in the series, the ideas described in it are counterintuitive and can be accidentally dismissed too soon without reading the main post first. Everything described here can be modeled mathematically—it’s essentially geometry. I take as an axiom that every agent in the multiverse experiences real pain and pleasure. Sorry for the rough edges—I’m a newcomer, non‑native speaker, and my ideas might sound strange, so please steelman them and share your thoughts. My sole goal is to decrease the probability of a permanent dystopia. I’m a proponent of direct democracies and new... (read 3234 more words →)

Effective Utopia & Startup Way There: Math-Proven Safe mAX-Intelligence, Multiversal Alignment, Physicalized Computational Ethics...

ank

AXI.now and maxintelligence.org web addresses are the direct links to this article.

(This is the result of three years of modeling hyper‑futuristic and current ethical systems. The first post in the series. Everything described here can be modeled mathematically—it’s essentially geometry. I take as an axiom that every agent in the multiverse experiences real pain and pleasure. Sorry for the rough edges—my ideas might sound strange, new ideas were added to this articles and made it a bit disjointed at places, please steelman and share your thoughts. My sole goal is to grow the best ethical ultimate future probability - p(best). New technologies can be a choice, not an enforcement upon us.)

Some of... (read 11819 more words →)

How To Prevent a Dystopia

ank

(Just edited this first post of mine, now it's obvious I don't propose to build any dystopias. I'm actually trying to prevent all the permanent enforced ones. This is the result of three years of thinking and modeling hyper‑futuristic and current ethical systems. It's the intro to the series, the ideas described in it are counterintuitive and can be accidentally strawmaned without reading the main post first. Everything described here can be modeled mathematically—it’s essentially geometry. I take as an axiom that every agent in the multiverse experiences real pain and pleasure. Sorry for the rough edges—I’m a newcomer, non‑native speaker, and my ideas might sound strange, so please steelman them and... (read 208 more words →)

-3