For those reading the paper: the positives of a good-view JEPA are described as “two observations of one scene,” and yet the paper also states that “A good-view JEPA's positives are (g_m(z, ν), g_m(z′, ν′)) with (z, z′) ∼ π and independent nuisances.” My question is: why doesn't “two observations of one scene” mean that both observations share the same underlying world state (z) and differ only in their modality nuisances (ν and ν′)? Also, I don't understand what “a symmetric positive-pair distribution (z, z′) ∼ π_m” (or more explicitly, a “world kernel”) means.

There are thousands of images and thousands of different crops from the images. Some are not solvable, but on average you can solve most of them!

For the world record, it would be nice to have the same daily challenge for everyone, but I actually like to lay a few games the same day.

I played like 3 games and I already saw a few repeated images (in different games).

There was a very old post in HN about "Cats as placeholder images" and one trick they used was to crop it to the correct size using the eye as the center, to ensure the part of the image was "interesting". Eyes make images interesting.

I only can beat Grok :(

The repeated images might be due to a ranking algorithm that samples random images. Since not all crops are solvable, images where many people achieved a decent score end up ranking higher.

I think it's a good idea to rank the images. Anyway, I expect repeated cases to be easier for people and skew the results.

By the way, the server is down until Monday, when we'll be able to reach the office.

Unless, of course, only the first attempts count toward the leaderboard.

Given two crops of the same image, determine their position relative to each other.

"Flying Machines Which Do Not Fly" is an editorial published in the New York Times on October 9, 1903. The article incorrectly predicted it would take one million to ten million years for humanity to develop an operating flying machine. It was written in response to Samuel Langley's failed airplane experiment two days prior. Sixty-nine days after the article's publication, American brothers Orville and Wilbur Wright successfully achieved the first heavier-than-air flight on December 17, 1903, at Kitty Hawk, North Carolina.

In her essay Economia di guerra e inquadramento della società in URSS (The War Economy and Social Control in the USSR), Rebecca Manley writes that initially the German advance in Russia was welcomed by the local population and threatened the legitimacy of the reigning power, while party leaders, officials, and factory managers often jumped ship, with the abandoned populace openly cursing them [A. Aglan and R. Frank, La guerra-mondo 1937-1947 (The World War 1937-1947), Einaudi, 2015-16]. Her account goes on to describe the government's gradual reassertion of control: The cost in human lives was increasing and shortages were continuing to worsen [...] it was only with the victory of Stalingrad that Stalin and the Soviet system recovered a central role in war propaganda. Overall, according to this author, the war years saw a surge of popular patriotism, even among those who had reason to distrust the State. The authorities in Moscow maintained order on the home front, something that those of the Tsarist Empire had failed to do.

The disorientation of non-Russian nationalities In the Russian countryside, and particularly in the three Baltic countries, Ukraine, the Caucasus, and Belarus, many had anxiously waited for the Germans as saviours and liberators from the Russian yoke [István Deák, Europe on Trial, Hachette UK, 2015]. However, the peasants soon felt deceived by those in whom they had initially trusted, because the Germans did not dismantle the collective farms (the kolkhoz) into which their lands had been forcibly incorporated. The Germans conserved the kolkhoz, because they were afraid production would fall otherwise, and, on the contrary, increased forced requisitions. The Russian government did form assault groups, recruited among the detainees in the forced labour camps, but, in the main, these were anti-Bolshevik Russian nationalists, motivated by patriotism. In contrast, prisoners of subjugated nationalities, such as the Poles, Ukrainians, and Balts, often escaped to join the Germans. On the whole, releasing anti-Stalinist political prisoners to enrol them in the army was forbidden; indeed, as we have already seen [Internationalism, April 2026], standing orders were to shoot all prisoners in the event of a forced retreat due to the German advance.

In assessing the present-day irruption of artificial intelligence, especially so-called generative AI based on highly effective linguistic-probabilistic systems, the starting point is to recognise that what is at stake is the development of the productive forces. The next step is to relate the critical aspects of AI – so hotly debated in the struggle between capitals who have a stake in it – not primarily to the intrinsic character of the technology itself, but to the fundamental contradiction between the development of the productive forces and capitalist relations of production.

First, for Engels, the brain is a product of labour. It is in the dialectical relationship of mutual action and reaction with labour – made possible by the articulation of the hand freed by man's upright posture, the result of "hundreds of thousands of years" of natural selection – that the brain evolved to perform the most complex functions and develop self-awareness. In turn, labour is an expression of the social relations at the basis of specific socio-economic formations across successive modes of production. Therefore, the brain is a social product, mediated by the hand that wields the tool, by labour that puts it in relation with the brains of other humans, and by the language made necessary by those relations.

Second, this relationship of upright posture-hand-language-brain, and the role played by labour in humanisation, is neglected by current conceptions and is also unrecognised by Darwinian evolutionists themselves. This is because the division into classes and the separation between manual labour and intellectual labour – in the latter's connection with the ruling class and its apparatus (schools, the Churches, etc.) – has led to the prevalence of the idealist conception that gives prominence to the brain and its representations.

Third, humanity has applied science to nature, and nature has thereby been modified through science, technology, and labour. But it has been difficult to go beyond the initial and immediate effects of this transformation, barely taking into consideration its secondary and long-term effects.

Fourth, and even more importantly, science has not been applied to the social consequences of labour and to its implications, from the division of labour to class struggle, thus depriving humanity of a vision of the wider, long-term effects of productive activity. Bourgeois economic science, i.e., classical political economy, has been unable to go any further. In order to regulate human labour activity according to a truly conscious plan, knowledge is not enough; an overturning of the mode of production and social order is necessary.

Fifth, the individual capitalist is concerned only with immediate profit, not with what will happen to the commodity or the buyer afterwards. The same applies to what will happen to nature and – we might add – to human nature itself.

More wars; there could be even a world war! All caused by imperialist competition between powers: the US, China, the EU, India, Brazil, Russia, etc. More nationalism (even with continental flavor like European nationalism), more militarism, more revolts, and possibly internationalist revolutions to unite the global working class against all wars and nationalisms!

I see these wave-like patterns on this lake. Are these aliasing artifacts?

Could they be real water waves? Perhaps from boat wakes?

"It [Anthropic] said DeepSeek's operation involved over 150,000 exchanges". In my humble opinion, a mere 150k exchange for an LLM could only be a benchmarking and not a distillation! I think the US companies should accept that after decades they have rivals surpassing them, just like they did Europeans almost a century ago.