Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Predicting the next word "only" is sufficient for language models to learn a large body of knowledge that enables then to code, answer questions, understand many topics, chat, and so on. This is clear to many researchers now, and there are nice tutorials on why this works by Ilya...

134,252 görüntüleme • 2 yıl önce •via X (Twitter)

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

AI Is Moving Beyond “Generating Videos” — Toward “Generating Worlds” Over the past two years, AI video models have advanced at an astonishing pace. From Runway and Pika to Sora and Veo, AI-generated videos have become increasingly realistic and more consistent with the physical laws of the real world. Many people believe the next objective is simply to generate videos that are longer, sharper, and more lifelike. But if we take a step back, we can see that the real transformation is not happening in video itself. It is happening in world models. What Is a World Model? In 1943, psychologist Kenneth Craik proposed an idea that would influence artificial intelligence research for decades. He argued that the human brain does not merely react to the outside world. Instead, it maintains an internal model of how the world works. Because we have this internal model, we can predict the outcome of an action before we actually take it. Before crossing a road, we estimate whether a car will pass by. Before catching a ball, we predict its trajectory. These abilities come from continuously simulating the world in our minds, rather than relying entirely on trial and error. This idea later became known by a more formal term: World Model. A world model does not describe a single image or a fixed video clip. It is an internal representation capable of continuously simulating the rules and dynamics of the real world. Why Is AI Research Turning Toward World Models? Because predicting “what comes next” is becoming increasingly central to how AI systems work. Language models predict the next token. Image models predict the next step in the denoising process. Video models predict the next frame. A world model, however, attempts to predict something broader: What should the world look like in the next moment? In 2018, David Ha and Jürgen Schmidhuber proposed in their paper World Models that an intelligent agent could first learn a model of the world, and then use that internal model to plan its actions. The Dreamer series later demonstrated that many complex tasks could be learned by training agents inside an “imagined world.” At the same time, the development of video models such as Sora and Veo led researchers to another realization: A model capable of continuously generating video has already learned, at least implicitly, many of the rules governing the real world. As a result, these two research directions have gradually begun to converge. But Video Is Not Yet a World This is where the distinction is often misunderstood. For a world model to support meaningful real-time interaction, it must solve several critical problems. Most video models today are essentially answering one question: What should the next frame look like? A true world model needs to answer much more: What happens if I take one step forward? If I walk behind a building and then return, will the building still be there? If I suddenly change the camera angle, will the entire space remain consistent? If I enter a command such as: “Summon a dragon.” Will the world respond immediately? In other words, a world model must do more than generate content. It must understand space. It must understand time. It must understand causality. And it must understand interaction. Moving from watching to participating is where the real difficulty of world models begins. World Models Are Entering the Interactive Era One of the latest attempts in this direction is Alaya World, recently open-sourced by Alaya World, or Alaya Lab. Instead of generating a fixed video clip, it generates a world that users can explore in real time. Users can begin with text, an image, or a video, enter the generated scene, move freely through it, and introduce new prompts at any moment during generation. The world responds immediately. According to the publicly released information, Alaya World provides: Real-time streaming generation at 720p and 24 FPS Stable continuous exploration for more than one minute The ability to switch prompts and trigger skills or events during generation Model weights and inference code released under the Apache 2.0 License Training code and datasets planned for future release What makes these capabilities important is not simply the technical specifications. It is that the generated “world” can now support continuous interaction. The official demo shows that users can genuinely control, transform, and explore the generated environment. AI Is Evolving From a Tool Into an Environment Over the past few years, most discussions around AI have focused on content generation. Generating text. Generating images. Generating videos. But world models raise a fundamentally different question: Can AI generate an environment that people can inhabit, explore, and continuously evolve? If the answer is yes, the impact will extend far beyond video generation. Game development, robotics training, embodied intelligence, digital twins, virtual production, and many other fields could be transformed by the development of world models. World models are still at a very early stage. Yet from Craik’s proposal of an internal mental model more than eighty years ago to the emergence of today’s interactive world-generation systems, a clear evolutionary path is beginning to take shape. Perhaps what AI is ultimately learning has never been limited to images, videos, or language. Perhaps it is learning the world itself. References GitHub: Technical Report:

雪踏乌云

112,114 görüntüleme • 13 gün önce

They did not take cursive from the schools because children no longer needed it. They took it because of what it was quietly building in them. Consider what the exercise actually is. A child, six years old, is handed a pen and asked to draw a single unbroken line that becomes a word. The wrist must float. The fingers must hold a living pressure, never quite the same twice, always correcting. The eye must follow the ink forward and trust the hand to finish what it has begun. There is no lifting, no stopping, no starting over mid-word. The loop must close. The ascender must rise and return. The sentence must travel from one margin to the other as a single continuous gesture, and at the end of it the hand must still be steady. Twelve years of this. Every day. Ten thousand small acts of sustained, self-correcting attention, carried out below the level of conscious thought, until the motion belongs to the body and the body belongs to the motion. This is not penmanship. It is the slow construction of an interior form. The hand that has learned to carry a line without breaking it is the hand of a mind that has learned to carry a thought without breaking it. The two are not metaphors for one another. They are the same faculty, trained in the same child, by the same daily discipline. Continuity of the stroke becomes continuity of the reasoning. The patience of the loop becomes the patience of the argument. The commitment to finish a word one has started becomes the commitment to finish a sentence, a paragraph, a life's idea, without reaching for the nearest distraction halfway through. Print is a different creature entirely. Print lifts. Print stops. Print assembles a word out of separate, stamped, interchangeable pieces, each one beginning and ending in isolation. A mind raised only on print learns to think the way print is made, in discrete tokens, in replaceable units, in fragments that can be recombined by any outside hand without the owner noticing the substitution. It is precisely the shape of thought a language model produces. It is precisely the shape of thought a language model can steer. Cursive is kata. This is the whole of it. A form repeated daily, for years, not for the sake of the form but for what the repetition lays down in the practitioner beneath the form. The swordsman does not train kata so that one day he may fight in kata. He trains it so that when the moment comes and there is no time to think, the movement is already inside him, older and deeper than thought, and it rises on its own. Cursive was the kata of the literate mind, the daily quiet drilling of continuity, of patience, of a line held steady under the long pressure of its own length. And the signature it produced at the end, that small flourished mark unique to a single human being on earth, was only the outward proof of an inward form no machine and no other hand could ever reproduce. Take the kata away and the practitioner is left with vocabulary in place of faculty. He can recognise a whole thought when he encounters one. He cannot carry one himself. He can admire a finished argument. He cannot sustain one long enough to close its loop. He begins books he does not finish, sentences he does not end, ideas he abandons the moment the screen in his palm offers him a brighter one. And when the machine begins feeding him tokens in the exact shape his schooling taught him to receive, he meets it with no interior resistance at all, because no interior form was ever built in him to push back with. They removed it quietly, across a generation, and they removed it in the last years before the machines arrived. Twelve years of daily practice in unbroken, embodied, self-authored thought, gone from the curriculum of almost every child in the Western world, just as the instruments designed to complete their sentences for them came online. The hand forgets. The mind, having never been taught the kata, forgets a thing it never knew it had. That is what cursive was. That is what was taken. And that is why the thought of anyone who still writes by hand, in long unlifted lines, remains, quietly, stubbornly, and without their ever needing to announce it, their own. Now the question stands open. What else has been banned, phased out, quietly retired from the curriculum and from common life over these same decades, under the same soft excuses? Mental arithmetic. Memorisation of poetry. Latin. Logic as a formal subject. Map reading. Knot work. The keeping of a commonplace book. The reading aloud of long passages in class. Singing in parts. What was each of those actually building in the child, beneath the surface of the lesson, and whose interest was served by its disappearance?

SiriusB

442,518 görüntüleme • 3 ay önce

Today I was visiting the exceptionally beautiful Plantin-Moretus Museum in Antwerp, Belgium (one of the only museums in the world that is itself listed as UNESCO World Heritage), which is one of the oldest printing shops in Europe, with the oldest surviving printing presses in the world. I stumbled upon an old 16th century atlas - written in Old French - and I was pretty amused to read their understanding of China at the time, which was surprisingly accurate, maybe even more than today's! A translation of some of the most interesting passages: - They call it "China" in French (it's now called "Chine") and they write that the locals call it "Tangis", which probably refers to the Tang dynasty but which is strange given that by the 16th century the dynasty had already ended for about 600 years - They write that to its North China is bordered by "tartares" (which I guess means Mongols) whom they describe as "very warlike people from whom it is separated by a wall made by hand" - The Chinese work ethic was already legendary: "those who live there are not at all lazy but devoted to labor and work, because it is there a shameful thing to be idle" - They share a number which must have seemed astonishing at the time: "in the city of Canton, one of the smallest in the entire country, some ten or twelve thousand ducks are eaten daily at table". And then they marvel during a good proportion of the text about the abundance of food in the country, which probably made a big impression on travelers at the time. - They write that "there are in this kingdom two hundred and forty famous cities, whose names end in this syllable FU which means a city: like Cantonfu, Panquifu: the small towns, which are in great number, end in CHEU [undoubtedly refers to "zhou"]. There are infinite villages, heavily populated, because of the continuous agriculture." - China's infrastructure and engineering capabilities were also already legendary at the time: "The city gates have entrances magnificently and marvelously well made, the streets are made level, not sloping this way or that, but following their straight line. They are so wide that ten or fifteen men on horseback can march abreast and are everywhere marked and separated by triumphal arches that marvelously ornament the cities. Portuguese say they saw in the city of Fuchco [probably Fuzhou] a tower set on forty solid marble pillars, the height of which was forty palms (masonry measure) and the width twelve: that this work is so grand, so exquisitely made, so beautiful to see, so sumptuous and so pleasing that it far surpasses all the magnificent buildings of all Europe." - Already at the time, China was very wary of safeguarding its sovereignty: ""[The Chinese] rarely or never leave their country and do not easily let foreigners enter it, especially into the interior of the province, unless they first have safe conduct from the king." - On moral and cultural habits: "They put adulterers to death. There are no brothels in the cities, all manner of prostitutes being sent to the suburbs. They celebrate their weddings at the time of the new moon and around the month of March which is their first day of the new year, and they make these celebrations, like us, very magnificently. They show themselves valiant in banquets and entertainments, in which they owe nothing to the Flemings or the Germans. They eat at tables like us in Europe, on chairs or on benches, and not on the ground as other peoples of Asia do." - On justice: "Bandits and murderers are kept in perpetual prison. Theft, which is a very odious crime, is punished by whip strokes in this manner: they put a man belly down, tie his hands behind him, striking him on the fleshy part of the legs with a whip made of reeds or canes." - On China's naval capabilities at the time: "This kingdom has an infinite number of ships, galleys and vessels of all sorts, with which they cross the seas and rivers. So much so that when they want to show through vainglory the power of their king, they are accustomed to say in a common proverb that he can make a bridge of ships joined together, which can reach and extend from China to Malacca, which is a distance of five hundred leagues and more." - On the emperor and China not being warlike (already back then): "All this region is subject to a single king, like a monarch; whom they call lord of the world and son of the sun. He holds court at Paquin [Beijing], which is a city toward Tartary. He never leaves it, except in time of war. It is said that when he makes war on the Tartars he leads an army of three hundred thousand soldiers and two hundred thousand horses, although it is also said that this nation is not very warlike. This king has under him fifteen very large provinces, which they call governments, and he alone surpasses in power all the other neighboring princes of Asia; and his annual revenues exceed all the riches of Europe. Antonio Pigafetta [the chronicler of Magellan's voyage] calls this king the most powerful of all the universal earth and says that the royal city is fortified and ramparted with seven walls, having ten thousand soldiers for the guard, and that the king commands seventy other crowns of the royal diadem [likely refering to the tributary state system]." Reading these passages, it seems that the further we've come in our ability to know China, the more obscured our vision seems to have become. These 16th century observers, working with fragments brought back by explorers, merchants and missionaries, managed to capture the essential - the industriousness, the engineering mastery, the administrative sophistication, the careful sovereignty. They approached their subject with the humility of the genuinely curious. They had no framework to force China into, no predetermined narrative to fulfill. They simply watched, counted ducks in Canton, measured city walls, and wrote it down. Their errors were errors of transmission - a dynasty name lingering centuries past its time, numbers perhaps inflated through retelling - but the spirit was one of simply describing unknown territory, not to convince anyone of anything. Today however, drowning in information, we're somehow seeing less of what's there and more of what we expect to find. Each observation must fit into existing narratives, serve predetermined conclusions, advance familiar arguments. So much so that we must ask ourselves: have we actually moved backward from those 16th chroniclers? Maybe we need to re-learn to approach China - and others in general - like those old cartographers, pen in hand, ready to be surprised? What might we discover if we stopped explaining and started counting ducks again?

Arnaud Bertrand

19,380 görüntüleme • 11 ay önce

❗️Girl shouts 'help' and the world closes its eyes❗️ The Iranian regime is sending morality police back onto the streets. “From Sunday, units of the moral police will go out on foot and by car across the country to detect violations”, according to Iran's Isna news agency. The fact that they want to take very strict action again, to maintain the oppression of women, is only thanks to the self-confidence that the ayatollahs and terrorists like Zakani are given by the West. Because whatever they do, it is not punished by the west, on the contrary...it is even rewarded. Zakani, the mayor of Tehran, better known as the Butcher of Tehran, installs cameras to identify, catch and punish women who commit a "violation" of the dress code with whipping or even murder, as they did with #MahsaAmini. And the Belgian government gives such a person a visa to come to Brussels so he can give a speech at city hall on how to deal with “security” in a big city. It seems like a sick joke but unfortunately it is true. And then terrorist Zakani returns to Iran, is promoted because of his successful trip and family in Iran of dissidents in Belgium, who have taken to the streets against his coming to Brussels, are intimidated, and I am discussed and threatened on Iranian state television as an "opposition leader". Doesn’t Belgium see the direct result of what they are now causing in Tehran? No, they are just once again soothing their non-existent conscience by continuing to justify the unnecessary presence of that "mayor" under the guise of "diplomacy". And this while brave girls and women are the only freedom soldiers standing up against the dogmas of religious oppression by those Islamists at the risk of their lives. While the West offers nothing of support and only exhibits hollow words and deeds, thus only supporting the regime. Iranian women will continue. It is up to the west to really support them instead of continuing to be so hypocritical. Not just for Iran, but for the world.

Darya Safai MP

88,501 görüntüleme • 3 yıl önce