CuriousJust @OrDisorder

Anthropic 俩工程师花了24分钟，把 Claude Code 里那些你压根不知道的隐藏功能全给扒干净了——关键是，免费看。 大多数人刷到就划走了。 但聪明人都会点进去看完。

The circular diagram presents the C major scale, its seven diatonic triads (I–vii°), and the corresponding relative modes in a single, integrated view. At its center lies C, from which the primary triads radiate outward: CM (I), Dm (ii), Em (iii), FM (IV), GM (V), Am (vi), and Bdim (vii°), each formed by stacking every other note of the C–D–E–F–G–A–B scale. Encircling these are the seven modes: Ionian, Dorian, Phrygian, Lydian, Mixolydian, Aeolian, and Locrian aligned with their respective parent roots and annotated with their characteristic scale degrees and interval patterns. This unified layout enables musicians to quickly visualize harmonic relationships, making it a practical reference for composition, improvisation, modulation, and transposition across keys.

FREE Classic Math Book, from the mentor of the Indian mathematician Srinivasa Ramanujan. Now online. 472 pages. "A Course of Pure Mathematics" by G.H. Hardy. 1. Real Variables 2. Functions of Real Variables 3. Complex Numbers 4. Limits of Functions of a Positive Integral Variable 5. Limits of Functions of a Continuous Variable. Continuous and Discontinuous Functions 6. Derivatives and Integrals 7. Additional Theorems in the Differential and Integral Calculus 8. The Convergence of Infinite Series and Infinite Integrals 9. The Logarithmic and Exponential Functions of a Real Variable 10. The General Theory of the Logarithimic, Exponential, and Circular Functions This is the classic textbook on introductory mathematical analysis. First published in 1908, it went through ten editions (up to 1952) and several reprints. It remains one of the most popular books on pure mathematics. Link: archive.org/details/course…

Marvin Minsky, MIT professor and father of artificial intelligence: "Anthropic pays engineers $900K to build multi-agent AI systems. The blueprint is 40 years old, from an MIT professor who proved intelligence is just a swarm of dumb specialists." the thread above shows you how to turn one AI into a team of specialized agents, each with its own job and memory, all managed by a boss. brilliant. it is also marvin minsky's 1986 theory of how your own mind works. minsky's whole idea was that intelligence is not one smart thing. it is a society of tiny, mindless agents, each doing a single dumb job, none of them intelligent alone. put enough of them together under a few managers and intelligence emerges. that is not a metaphor for the claude trick. it is the claude trick. so when you spin up specialized sub-agents and delegate, you are not inventing a new hack. you are rebuilding the architecture minsky described forty years ago, the same one your brain has run your entire life. he co-founded the field, taught it at MIT, and left it all in this free lecture. same story i keep telling: the "new" AI trick is usually an old idea in a new wrapper. here is the part the thread skips, and minsky knew it. a society of agents is only as good as how you organize it. one dumb specialist is useless. a thousand, badly managed, is chaos. the edge was never spawning the agents. it is the orchestration, knowing which specialist to call, when, and how to combine their answers. the tool is free. the judgment is the whole game.

Atenov int. @Atenov_D

2 days ago

x.com/i/article/2074…

23 11 105 158K 173

Anthropic 这次是真把饭喂到嘴边了。 一门 4 小时免费课，直接教你怎么把 Claude 用到 AI 工程岗位级别，目标还是年薪 50 万美元那种。 重点别乱看，直接跳这些： 00:15 正确提示 Claude 33:21 哪些操作会让 Claude 在代码上变笨 01:33:39 Anthropic 内部每天怎么用 Claude 02:50:56 怎么修 Claude，让它重新变聪明 最夸张的是，这课免费。 信息密度基本顶 10 门付费工程课，很多人花几千块买的课，可能还没它讲得硬。 先把视频看完，再去看那个构建 loop 的逐步指南。 说白了，差距已经不是你会不会问 Claude。 是别人已经开始让 Claude 自己循环干活了。

3小时从零构建LLM实录！ LLM入门→Transformer架构→训练全流程→模型现代化改造→扩展实战 边讲边敲代码，全程可见 想搞懂ChatGPT/Claude底层原理看👀🔥 #AI #LLM #大模型

π can be reached through many elegant mathematical routes, including its decimal expansion, continued fractions, arccos(-1), arctangent combinations, definite integrals, infinite products, series like BBP and Ramanujan, and arithmetic-geometric mean iterations. It is used to enable precise numerical computation of the constant in computational physics and cryptographic systems.

史丹佛發布了一門免費課程，從內到外解釋 Claude 和 ChatGPT 的工作原理。 大多數人將潛力的 90% 白白浪費，而史丹佛在 1 小時 44 分鐘內傳授這項知識。

Google 近日发布了一门从零开始讲 Agentic Engineering 的 1 小时课程： – 如何构建你的第一个 AI Agent – 构建 Agent 记忆 – Agentic Loop，以及长时间运行的 AI Agent – 如何构建 MCP：MCP 与 API 的区别 – 多 Agent 系统 足以替代网上 10 门付费 Agentic 课程。

剑桥这波直接放大招了！！ AI & ML 经典教材全集免费公开，PDF随便下。 想入坑机器学习又不想被割韭菜买天价课的，这十本啃完，地基基本就稳了。 顺序排好了，从入门到进阶： 1️⃣ 机器学习理解，讲透理论和算法，入门首选 🔗 cs.huji.ac.il/~shais/Underst… 2️⃣ 机器学习数学基础，数学欠火候的先补这本 🔗 mml-book.github.io/book/mml-book.… 3️⃣ 机器学习算法的数学分析 🔗 tongzhang-ml.org/lt-book/lt-boo… 4️⃣ 深度学习理论原理 🔗 arxiv.org/pdf/2106.10165 5️⃣ 神经网络与机器学习 🔗 arxiv.org/pdf/1901.05639 6️⃣ 图深度学习 🔗 yaoma24.github.io/dlg_book/dlg_b… 7️⃣ 机器学习的算法视角 🔗 people.csail.mit.edu/moitra/docs/bo… 8️⃣ 概率论：理论与实例 🔗 sites.math.duke.edu/~rtd/PTE/PTE5_… 9️⃣ 应用概率基础 🔗 sites.math.duke.edu/~rtd/EP4A/EP4A… 🔟 高级数据分析 🔗 stat.cmu.edu/~cshalizi/ADAf… 说实话，这些书难度都不低，别指望躺着刷完。 但只要你真下定决心啃两三本，比在群里听人吹AI牛逼强一百倍。

Download 698-page PDF eBook… Everything You Always Wanted To Know About Mathematics* (*But didn’t even know to ask) A Guided Journey Into the World of Abstract Mathematics, Theorems, and the Writing of Proofs: math.cmu.edu/~jmackey/151_1…

"Problem-Solving Strategies" by Arthur Engel One of the most popular books among students preparing for math competitions. archive.org/details/Proble…

MIT 那本《计算机科学数学》，我劝真想搞计算机的赶紧存，这玩意儿基本是天花板了。 先别被 1048 页吓尿，厚归厚，人家就是写给初学者的入门书。我第一眼也懵：1048 页也配叫入门？翻进去才懂，它不催你一口气啃完，是把最底子的东西掰碎了喂你，慢慢来跟得上。 真想学的听我一句：别再收藏那些速成课了，这种硬货啃一本，顶你刷十个短视频。 🔗 pan.quark.cn/s/407bddee8a74

Google工程师刚刚直播手搓了个完整App。 全程就靠Claude，一个人26分钟搞定。 用的就是他们内部的工作流，不需要团队，小白也能照做。 这比那些500美刀的摸鱼编程课实在多了。 视频下面还附了份指南，告诉你Claude里99%的人都不知道的隐藏功能。

淘沙者(TheSandPicker) @Etudecn

6 days ago

x.com/i/article/2075…

2 65 228 418K 602

Andrej Karpathy 把大模型说透了。 “LLM 压根没想成功，它只想模仿。” 他最近在微软 Build 大会有个 42 分钟的演讲，把模型到底怎么“想”的掰开揉碎了讲。 没有野心，不追求“正确”，就是重复训练时见过的模式。 最绝的是这个对比：一个 80 层 Transformer 处理一个 token 的算力，跟你大脑处理一个念头的能耗差不多。 这不是什么提示词魔法，这是理解模型的底层逻辑。 比网上那些卖 500 美金的神棍课值钱多了。 想停止把 AI 当人一样许愿，开始把它当工具一样使用？这个演讲是必修课。 看了没？没看赶紧去。

Learn Probability Through Problems (exercises, hints, and solutions provided): amzn.to/3vZed8W ————— #Statistics #DataScience #Mathematics #DataScientist

Stanford, Claude ve ChatGPT'nin çalışma mantığını içten dışa açıklayan ücretsiz dersi yayımladı. Çoğu insan potansiyelinin yüzde 90'ını boşa harcarken, Stanford bu bilgiyi 1 saat 44 dakikada öğretiyor. Kaybetmemek için favorilere ekleyin.

冯·诺伊曼是人类历史上最聪明的脑袋之一，现代计算机和博弈论之父。从接触计算机开始，他一直是我的偶像。 在20世纪那个大师辈出、神仙打架的年代，毕竟有爱因斯坦、薛定谔、费米、奥本海默、图灵同台竞技，冯·诺伊曼依然是所有人公认的外星人。 当时普林斯顿高等研究院流传着一个极其著名的段子：“冯·诺伊曼其实不是地球人，他是一个进化得极其完美的、伪装成人类的外星人，因为他能把人类的语言和行为模拟得天衣无缝。” 他没工夫跟普通天才玩虚的，简单来说，他靠无双的算力和降维打击的抽象能力，在许多领域直接开宗立派。 计算机。 他写了一篇101页的报告，规定了数据和指令要放在一起用二进制存储。今天无论是你桌上的高配PC，还是运行ChatGPT的英伟达H100服务器，全都是冯·诺伊曼架构的重孙子。 数学。 别人一辈子研究不透一个细分，他20多岁时顺手给整个现代数学的集合论修好了地基，接着又用泛函分析给满是玄学的量子力学发了合法营业执照。 经济与博弈。 他写了一本书叫《博弈论与经济行为》，生生发明了博弈论。从此以后，华尔街的收割模型、冷战时期的核威慑战略、甚至我在PUBG里卡掩体的心理博弈，底层全在走他的数学账本。 原子弹。 曼哈顿计划里神仙打架，遇到原子弹核心爆轰的流体力学地狱难题时，大佬们全卡壳了。冯·诺伊曼走过去闭眼心算了几分钟，甩出了内爆形貌设计方程，直接给核武器发了通关通行证。 还有许许多多领域，他开创着，构建着…… 他活着的53年里，几乎凭一己之力，把人类文明在数学、物理、计算机和经济学上的进度条，强行往后暴拽了至少半个世纪。 冯诺伊曼不需任何吹捧，他就是那个时代的神。

FREE Math Book. "Notes on Algebraic Structures" by Cameron. Everything you wanted to know about Rings and Groups. 1 Introduction 1.1 Abstract algebra 1.2 Sets, functions, relations 1.3 Equivalence relations and partitions 1.4 Matrices 1.5 Polynomials 1.6 Permutations 2 Rings 2.1 Introduction 2.1.1 Definition of a ring 2.1.2 Examples of rings 2.1.3 Properties of rings 2.1.4 Matrix rings 2.1.5 Polynomial rings 2.2 Subrings 2.2.1 Definition and test 2.2.2 Cosets 2.3 Homomorphisms and quotient rings 2.3.1 Isomorphism 2.3.2 Homomorphisms 2.3.3 Ideals 2.3.4 Quotient rings 2.3.5 The Isomorphism Theorems 2.4 Factorisation 2.4.1 Zero divisors and units 2.4.2 Unique factorisation domains 2.4.3 Principal ideal domains 2.4.4 Euclidean domains 2.4.5 Appendix 2.5 Fields 2.5.1 Maximal ideals 2.5.2 Adding the root of a polynomial 2.5.3 Finite fields 2.5.4 Field of fractions 2.5.5 Appendix: Simple rings 2.5.6 Appendix: The number systems 3 Groups 3.1 Introduction 3.1.1 Definition of a group 3.1.2 Examples of groups 3.1.3 Properties of groups 3.1.4 Notation 3.1.5 Order 3.1.6 Symmetric groups 3.2 Subgroups 3.2.1 Subgroups and subgroup tests 3.2.2 Cyclic groups 3.2.3 Cosets 3.2.4 Lagrange’s Theorem 3.3 Homomorphisms and normal subgroups 3.3.1 Isomorphism 3.3.2 Homomorphisms 3.3.3 Normal subgroups 3.3.4 Quotient groups 3.3.5 The Isomorphism Theorems 3.3.6 Conjugacy 3.4 Symmetric groups and Cayley’s Theorem 3.4.1 Proof of Cayley’s Theorem 3.4.2 Conjugacy in symmetric groups 3.4.3 The alternating groups 3.5 Some special groups 3.5.1 Normal subgroups of S4 and S5 3.5.2 Dihedral groups 3.5.3 Small groups 3.5.4 Polyhedral groups Link: cameroncounts.wordpress.com/lecture-notes/

“Introduction to Applied Linear Algebra: Vectors, Matrices, and Least Squares” 473-page PDF download here: web.stanford.edu/~boyd/vmls/vml…