YMC

An engineer built an interactive book on data structures and algorithms of 680 pages:

What !!!!!

Our paper was accepted as a #ICML2026 Spotlight! Reasoning in LLMs has improved largely by chaining local steps. But is that the whole story? Humans occasionally make inferential "leaps" across domains, a faculty known as analogy. We design a synthetic task to show how small Transformers acquire analogical reasoning, and find that the same signatures appear in pretrained LLMs. arxiv: arxiv.org/abs/2602.01992 code: github.com/gouki510/Analo…

@le_jt @Linformatrice1 🤣🤣🤡🤡

@Linformatrice1 L’Iran a promis d’utiliser la bombe sur Israël dès que possible. Israël a la bombe depuis 60 ans et ne l’a heureusement jamais utilisée. C’est subtile comme différence mais même toi peut être tu peux saisir

Le Sionistan n'a jamais soumis son programme nucléaire à approbation ni permis que l'on visite ses sites.

@arnoklarsfeld L'Iran ne veut pas la bombe atomique, et toi, et ton peuple élu, vous nous faites chier

This math sits underneath every AI model being trained right now. Gradient. Jacobian. Hessian. Three words that look intimidating at first. But they are really just three ways of measuring change. 𝟭. 𝗚𝗿𝗮𝗱𝗶𝗲𝗻𝘁 ∇f Takes a scalar function: f : ℝⁿ → ℝ Returns a vector of first-order partial derivatives. It answers: "Which direction makes f increase fastest?" That is why gradients are central to optimization. Gradient descent moves in the opposite direction because the gradient points uphill. Backpropagation efficiently computes gradients during training. 𝟮. 𝗝𝗮𝗰𝗼𝗯𝗶𝗮𝗻 J_F Takes a vector-valued function: F : ℝⁿ → ℝᵐ Returns an m × n matrix of first-order partial derivatives. It answers: "How does each output change with each input?" The Jacobian is the local linear map of a vector-valued function. It shows up in: → sensitivity analysis → change of variables → automatic differentiation → forward-mode AD → reverse-mode AD / backpropagation In simple terms: forward-mode AD uses Jacobian-vector products. reverse-mode AD uses vector-Jacobian products. 𝟯. 𝗛𝗲𝘀𝘀𝗶𝗮𝗻 H_f Takes a scalar function: f : ℝⁿ → ℝ Returns an n × n matrix of second-order partial derivatives. It answers: "How does the gradient itself change?" That means the Hessian measures curvature. When the second partial derivatives are continuous, the Hessian is symmetric. At a critical point: → positive definite Hessian → strict local minimum → negative definite Hessian → strict local maximum → indefinite Hessian → saddle point The clean mental model Gradient = first derivatives of one output → tells you direction Jacobian = first derivatives of many outputs → tells you sensitivity Hessian = second derivatives of one output → tells you curvature And the relationship between them is simple: The Hessian is the Jacobian of the gradient. For a scalar output, the Jacobian contains the same partial derivatives as the gradient, up to row/column convention. Same idea: measure change. Different object: direction, sensitivity, curvature. Once this clicks, optimization stops looking like a pile of formulas. It starts looking like a map of the problem.

@realmarcel1 Ce gars est vraiment con

Le concept c’est « Humiliated all around the world », si j’ai bien compris

Mercii Professeur Collon

@VincentLanies @Esban_ 💯

En intraveineuse svp

The Israeli ambassador to Denmark is protesting the spread of this video. Let's make this go viral all around the world."

@Mandogmatique @realmarcel1 Wai ta raison on aurait vraiment tout vu

@realmarcel1 Le gouvernement Macron qui se plaint du gouvernement Macron en faisant les éloges d’un prochain gouvernement Macron

Elle a pris un truc ?

instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale useful whether you've never built an agent in your life or have been using Claude every day for the past year I took the key ideas and turned them into a practical guide on how to actually build with Kimi find it below

@Lu226 @kirillk_web3 Maybe beacause Ai Suggest it

@kirillk_web3 Why do people always start with “instead of watching two hours of Netflix tonight”? It’s getting a bit old, isn’t it?

Maxwell’s Equations - the four fundamental laws of classical electromagnetism; shown in both integral and differential forms, alongside a 3D visualization of propagating electromagnetic waves. It illustrates Gauss’s laws, Ampere’s law (with displacement current), and Faraday’s law, with clear field diagrams for each. These equations describe and predict all electromagnetic behavior, enabling the design of antennas, radio/TV broadcasting, wireless communication, radar, electric motors, transformers, MRI scanners, fiber-optic systems, and virtually every modern electrical and electronic technology.

talented singer gives me a sample then goes OFF 🤯 youtube.com/shorts/Sa3tF23… via @YouTube

NYC park is a 90s hip-hop haven 🤯 youtube.com/shorts/7U0vsOi… via @YouTube

cellist sets off the most FIRE jam ever 🔥🤯 youtube.com/shorts/3vvEKZu… via @YouTube

Ce que ce témoignage montre sur @Francois_Ruffin… - C’est un mythomane - Pour lui barbu = arabe = violent visiblement. - Il est contre les abus policiers seulement quand ça interfère avec son emploi du temps - Il paie si peu lui même qu’il ne sait pas se servir de sa CB 😭

cellist sets off the most FIRE jam ever 🔥🤯 youtube.com/shorts/3vvEKZu… via @YouTube