Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

This project argues that latent space—the learned, multidimensional, representational substrate of neural networks—is not only a mathematical construct but, read through literature, a structure akin to architectural interiority that renders the abstract physically legible.

Gašper Beguš

8,823 subscribers

10,671 views • 6 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Ever wondered what neural networks are and how they work? Systems like ChatGPT use neural networks to work as well as they do. Neural networks are composed of "layers" of neurons, layers with different functions; connections between layers called "weights"; and mathematical functions called "activation functions". If you’re interested in learning about these systems, check the comments. Ultimately, the neural network structure of the model serves to visually demonstrate that it is, in fact, a complex mathematical equation. When companies release the model's weights, they are releasing a key component needed to run the model's complete equation. Without the weights, the equation is incomplete. For the math-minded: the weights of a model are the learned numbers (they are variables during training) that are then used as constants in the mathematical functions that make up the model. Neural networks are ultimately just one big, hyper-complex mathematical function, and when a model is trained, it learns the constants associated with the high-dimensional input.

Ever wondered what neural networks are and how they work? Systems like ChatGPT use neural networks to work as well as they do. Neural networks are composed of "layers" of neurons, layers with different functions; connections between layers called "weights"; and mathematical functions called "activation functions". If you’re interested in learning about these systems, check the comments. Ultimately, the neural network structure of the model serves to visually demonstrate that it is, in fact, a complex mathematical equation. When companies release the model's weights, they are releasing a key component needed to run the model's complete equation. Without the weights, the equation is incomplete. For the math-minded: the weights of a model are the learned numbers (they are variables during training) that are then used as constants in the mathematical functions that make up the model. Neural networks are ultimately just one big, hyper-complex mathematical function, and when a model is trained, it learns the constants associated with the high-dimensional input.

Harper Carroll

39,391 views • 11 months ago

New way to navigate latent space. It preservers the underlying image structure and feels a bit like a powerful style-transfer that can be applied to anything. The trick is to...

New way to navigate latent space. It preservers the underlying image structure and feels a bit like a powerful style-transfer that can be applied to anything. The trick is to...

Johannes Stelzer

313,952 views • 2 years ago

Drop everything and watch this…. Buried in the desolate heart of Rajasthan, Bir-ka-Khazana Bawdi rises not merely as a relic of Bharat’s ancient hydrological mastery, but as an architectural cipher a structure that encodes the diameter of the Earth, the lunar distance, and mathematical constants that modern science claims as its own. A stepwell that doubles as a cosmic instrument. A water reservoir that is, in truth, a geometric manifesto. No one comes even an inch closer to Sanatan Dharma… We are the world.. Unfathomable. Unassailable. UNBELIEVABLE

Drop everything and watch this…. Buried in the desolate heart of Rajasthan, Bir-ka-Khazana Bawdi rises not merely as a relic of Bharat’s ancient hydrological mastery, but as an architectural cipher a structure that encodes the diameter of the Earth, the lunar distance, and mathematical constants that modern science claims as its own. A stepwell that doubles as a cosmic instrument. A water reservoir that is, in truth, a geometric manifesto. No one comes even an inch closer to Sanatan Dharma… We are the world.. Unfathomable. Unassailable. UNBELIEVABLE

Comman Man

36,943 views • 9 months ago

Drop everything and watch this…. Buried in the desolate heart of Rajasthan, Bir-ka-Khazana Bawdi rises not merely as a relic of Bharat’s ancient hydrological mastery, but as an architectural cipher a structure that encodes the diameter of the Earth, the lunar distance, and mathematical constants that modern science claims as its own. A stepwell that doubles as a cosmic instrument. A water reservoir that is, in truth, a geometric manifesto. No one comes even an inch closer to Sanatan Dharma… We are the world.. Unfathomable. Unassailable. UNBELIEVABLE.

Drop everything and watch this…. Buried in the desolate heart of Rajasthan, Bir-ka-Khazana Bawdi rises not merely as a relic of Bharat’s ancient hydrological mastery, but as an architectural cipher a structure that encodes the diameter of the Earth, the lunar distance, and mathematical constants that modern science claims as its own. A stepwell that doubles as a cosmic instrument. A water reservoir that is, in truth, a geometric manifesto. No one comes even an inch closer to Sanatan Dharma… We are the world.. Unfathomable. Unassailable. UNBELIEVABLE.

Comman Man

48,152 views • 10 months ago

Evolution of the Scaling Era cover: “It’s hard to find unique ways of visualizing AI without defaulting to the obvious,” says Pablo Delcan. “In our design process, we experimented with unexpected metaphors—flowers growing out of neural networks, abstract mathematical puzzles like the Knight’s Tour—before arriving at a graphic visualization of an LLM: input, transformers, attention, multilayer perceptrons, and output. The result is a cover that is both direct and sculptural.”

Evolution of the Scaling Era cover: “It’s hard to find unique ways of visualizing AI without defaulting to the obvious,” says Pablo Delcan. “In our design process, we experimented with unexpected metaphors—flowers growing out of neural networks, abstract mathematical puzzles like the Knight’s Tour—before arriving at a graphic visualization of an LLM: input, transformers, attention, multilayer perceptrons, and output. The result is a cover that is both direct and sculptural.”

Stripe Press

143,742 views • 11 months ago

📁 Terence Tao, Fields Medalist mathematician, explains that neural networks do not understand concepts, but they uncover hidden patterns. In knot theory, a classical neural network discovered correlations between mathematical invariants no one had anticipated. It started as a black box, then became a real clue to deep structures humans had missed.

📁 Terence Tao, Fields Medalist mathematician, explains that neural networks do not understand concepts, but they uncover hidden patterns. In knot theory, a classical neural network discovered correlations between mathematical invariants no one had anticipated. It started as a black box, then became a real clue to deep structures humans had missed.

Jon Hernandez

204,985 views • 9 months ago

Elliot Page’s new documentary argues that animals prove gender is a social construct. The evidence? Dogs humping each other. This is one of the strangest attempts yet to use nature to push modern gender ideology.

Sensitive content

Elliot Page’s new documentary argues that animals prove gender is a social construct. The evidence? Dogs humping each other. This is one of the strangest attempts yet to use nature to push modern gender ideology.

Lauren Chen

43,820 views • 2 months ago

📁 Geoffrey Hinton, a pioneer of deep learning, says LLMs do understand what they say. He explains that understanding language is not translating it into an internal symbolic code. In neural networks, words act like Lego blocks that combine to form meaning. It is not translation, it is structure. That is what real language understanding looks like.

📁 Geoffrey Hinton, a pioneer of deep learning, says LLMs do understand what they say. He explains that understanding language is not translating it into an internal symbolic code. In neural networks, words act like Lego blocks that combine to form meaning. It is not translation, it is structure. That is what real language understanding looks like.

Jon Hernandez

77,752 views • 8 months ago

A mathematical rule this simple should not look this alive Thousands of Collatz trajectories are folded through symmetry and grow into something thats almost botanical... ordered, delicate and strangely natural. Nome of this proves the Collatz conjecture, of course, but it is striking to see so much structure come from a problem that still resists proof. Maybe AI systems will crack this one.

A mathematical rule this simple should not look this alive Thousands of Collatz trajectories are folded through symmetry and grow into something thats almost botanical... ordered, delicate and strangely natural. Nome of this proves the Collatz conjecture, of course, but it is striking to see so much structure come from a problem that still resists proof. Maybe AI systems will crack this one.

Mathelirium

22,778 views • 17 days ago

The Department of Education funded this NGO, which argues that white children must "push through all of the white fantasy that is just part of what it means to grow up in a white supremacist society." They believe that white children are not "innocent."

The Department of Education funded this NGO, which argues that white children must "push through all of the white fantasy that is just part of what it means to grow up in a white supremacist society." They believe that white children are not "innocent."

Christopher Rufo

388,049 views • 1 year ago

Excited to drive through refreshed Scandinavia? 🚛 Today, we're happy to share with you a look at some of the road networks we've been working on for this ETS2 DLC that is currently undergoing a refresh 🛣️ Read the blog here 👇

Excited to drive through refreshed Scandinavia? 🚛 Today, we're happy to share with you a look at some of the road networks we've been working on for this ETS2 DLC that is currently undergoing a refresh 🛣️ Read the blog here 👇

SCS Software

13,565 views • 1 year ago

.Bridgit Mendler on the founding thesis of Northwood. "We really were recognizing the same problem, that networking for the space economy is really what drives its value. And there's a significant bottleneck, and that bottleneck actually is not in space. It's actually on Earth. The way that you actually solve that networking problem for space is through introducing a model that gets you to the scale that you need, not just for one individual company or a mission, but for the industry overall." Full "Valley of Depth" episode in comments 👇

.Bridgit Mendler on the founding thesis of Northwood. "We really were recognizing the same problem, that networking for the space economy is really what drives its value. And there's a significant bottleneck, and that bottleneck actually is not in space. It's actually on Earth. The way that you actually solve that networking problem for space is through introducing a model that gets you to the scale that you need, not just for one individual company or a mission, but for the industry overall." Full "Valley of Depth" episode in comments 👇

Mo Islam

145,245 views • 3 months ago

According to Chris Mattei , this is defamation. She is not under oath. She is not reporting the allegation to authorities as a crime. But only making a declaratory statement of fact that happens to be in a gov setting, and that per se defames Karen Read. And the fact it is not true, proves it’s defamation. Thanks Chris! Now we know!

According to Chris Mattei , this is defamation. She is not under oath. She is not reporting the allegation to authorities as a crime. But only making a declaratory statement of fact that happens to be in a gov setting, and that per se defames Karen Read. And the fact it is not true, proves it’s defamation. Thanks Chris! Now we know!

Кarl Hungus

19,383 views • 2 months ago

Scientists found that only some bees can figure out how to do this on their own. But 60% of inexperienced bees watching this, learned the new skill [read more:

Scientists found that only some bees can figure out how to do this on their own. But 60% of inexperienced bees watching this, learned the new skill [read more:

Massimo

218,602 views • 3 years ago

Pastor Dawn Hutchings of Holy Cross Lutheran Church (ELCA) argues that Jesus did not physically rise from the dead, but only rose "spiritually." She further insists that Paul thought arguments about Jesus' bodily resurrection were "stupid" and not worth having.

Pastor Dawn Hutchings of Holy Cross Lutheran Church (ELCA) argues that Jesus did not physically rise from the dead, but only rose "spiritually." She further insists that Paul thought arguments about Jesus' bodily resurrection were "stupid" and not worth having.

Protestia

18,069 views • 3 months ago

We inaugurated Shabeely Resort, one of the flagship projects under the Dine for Generations initiative, which spans 385 hectares. Shabeely is not only a resort, but also a living expression of the rich heritage of the Somali Region, seamlessly blending modern architecture with ancient traditions. This eastern region project, among many others, marks a significant milestone in fulfilling our promise to make Ethiopia one of Africa’s top tourist destinations. The region’s abundant natural landscape, combined with the partnerships forged through Medemer’s endeavour, powerfully demonstrates that Ethiopia is not only a nation that dreams, but one that turns those dreams into reality.

We inaugurated Shabeely Resort, one of the flagship projects under the Dine for Generations initiative, which spans 385 hectares. Shabeely is not only a resort, but also a living expression of the rich heritage of the Somali Region, seamlessly blending modern architecture with ancient traditions. This eastern region project, among many others, marks a significant milestone in fulfilling our promise to make Ethiopia one of Africa’s top tourist destinations. The region’s abundant natural landscape, combined with the partnerships forged through Medemer’s endeavour, powerfully demonstrates that Ethiopia is not only a nation that dreams, but one that turns those dreams into reality.

Abiy Ahmed Ali 🇪🇹

145,325 views • 8 months ago

On of my favorite RPO concepts is a 2 back set that can be run to the read, or away. Gives the illusion of a stretch/lead run (& can convert to that), but the lead back is running an arrow route out of the backfield. Read the apex defender & make wrong! Pace N Space

On of my favorite RPO concepts is a 2 back set that can be run to the read, or away. Gives the illusion of a stretch/lead run (& can convert to that), but the lead back is running an arrow route out of the backfield. Read the apex defender & make wrong! Pace N Space

Mark Murdoch

12,609 views • 7 months ago