2026年6月14日 星期日

紀念 Herbert Simon 2026： 與 Jorge Luis Borges談 maze。 這一 ai overview 還可以： 共同的連結：西蒙發現，波赫士在《岔路花園》和《巴別圖書館》等作品中也探討了現實中這種分支迷宮般的本質。

 

紀念 Herbert Simon 2026： 與 Jorge Luis Borges談  maze。 這一 ai overview 還可以： 共同的連結：西蒙發現，波赫士在《岔路花園》和《巴別圖書館》等作品中也探討了現實中這種分支迷宮般的本質。

在自傳《我的人生模型》中，諾貝爾文學獎得主赫伯特·西蒙以迷宮為中心隱喻，探討人類的決策和人生本身，這一概念也讓他對豪爾赫·路易斯·博爾赫斯的作品產生了濃厚的興趣。西蒙認為他們是志同道合的夥伴，共同探索人類存在的迷宮本質。

迷宮隱喻：西蒙提出了一個「沒有彌諾陶洛斯的迷宮」。他認為，人生並非由宏大的陰謀或必須征服的怪物所驅動，而是一系列循序漸進的、局部性的選擇。有限理性：西蒙的迷宮模型表明，由於人類的認知能力有限（有限理性），我們在應對環境的岔路時，只能做出「足夠好」的選擇，而非數學上的最優解。


共同的連結：西蒙發現，波赫士在《岔路花園》和《巴別圖書館》等作品中也探討了現實中這種分支迷宮般的本質。

會面：這種共同的學術興趣促使西蒙於1970年前往阿根廷拜訪博爾赫斯。西蒙透過數學模型和電腦模擬得出迷宮的比喻，而博爾赫斯則透過文學作品得出這個結論。

西蒙的短篇小說：《我人生的模型》收錄了西蒙唯一一部小說作品——一個關於迷宮漫遊者的短篇小說，其靈感直接來自他的迷宮理論以及他與博爾赫斯的討論。

In his autobiography Models of My Life, Nobel laureate Herbert Simon uses the maze as a central metaphor for human decision-making and life itself, a concept that drew him to the work of Jorge Luis Borges. Simon saw them as kindred spirits exploring the labyrinthine nature of human existence. [1, 2, 3]
  • The Maze Metaphor: Simon proposed a "maze without a Minotaur". Rather than life being driven by a grand overarching plot or a monster we must conquer, he viewed human life as a series of stepwise, local choices. [1, 2, 3, 4]
  • Bounded Rationality: Simon’s maze model demonstrated that because humans have limited cognitive power (bounded rationality), we navigate the branching paths of our environments by making choices that are "good enough" rather than mathematically optimal. [1, 2]
  • The Shared Connection: Simon discovered that Borges explored this same branching, maze-like nature of reality in stories like The Garden of Forking Paths and The Library of Babel. [1]
  • The Meeting: This shared intellectual fascination prompted Simon to travel to Argentina to meet Borges in 1970. While Simon arrived at this maze metaphor through mathematical models and computer simulations, Borges did so through literature. [1, 2, 3]
  • Simon's Short Story: Models of My Life contains Simon's only attempt at fiction—a short story about a maze wanderer directly inspired by his maze theories and his discussions with Borges. [1, 2]

可信乎？

In his autobiography, Models of My Life, Nobel laureate Herbert Simon uses the metaphor of a maze to describe his life and career. Instead of making radical, wrenching decisions to change directions, he viewed his life as navigating a path of choices based on immediate opportunities and challenges. [1]
Simon details several key concepts and "models" regarding his journey:
  • Life is Like a Maze: Rather than perfectly plotting every step, people make choices constrained by their surroundings and circumstances. [1]
  • Bounded Rationality: He popularized the concept that human decision-making is constrained by limited information, time, and cognitive capacity. [1]
  • Satisficing: Instead of striving to find the mathematically "optimal" choice, individuals seek out solutions that are simply "good enough". [1]
  • Artificial Intelligence: As a pioneer in the field, Simon writes about the conceptual foundations of human intelligence as the rule-governed manipulation of symbols. [1, 2, 3, 4]


張貼者： 於 沒有留言:

2026年6月13日 星期六

紀念 Herbert Simon,2026 赫伯特·西蒙為現代複雜性科學奠定了基礎，而複雜性科學又為混沌理論提供了概念架構。西蒙的人類問題解決模型為後來的複雜性經濟學家和社會科學家建構混沌社會經濟系統模型提供了微觀基礎。名著《人工科學》中，西蒙著重探討了複雜環境如何與簡單的人類決策相互作用。本書的後續版本直接探討了混沌理論、遺傳演算法和複雜適應系統的出現，並將它們融入他對智慧系統（包括自然系統和人工系統）如何運作的更廣闊的願景中。 讀ben chen 介紹的 文章《混沌的五十年》（Fifty Years of Chaos）是由「混沌理論」的奠基人之一、數學家詹姆士·約克（James Yorke）所寫。本文的四大核心重點分析： 1. 混沌的本質：完全決定論的系統，依然無法預測 2. 混沌不是特例，而是世界的常態 3. 三大限制原則與混沌的實際應用 4. 警示未來：人工智慧（AI）是當代的「新混沌」

 



紀念 Herbert Simon,2026  赫伯特·西蒙為現代複雜性科學奠定了基礎，而複雜性科學又為混沌理論提供了概念架構。西蒙的人類問題解決模型為後來的複雜性經濟學家和社會科學家建構混沌社會經濟系統模型提供了微觀基礎。名著《人工科學》中，西蒙著重探討了複雜環境如何與簡單的人類決策相互作用。本書的後續版本直接探討了混沌理論、遺傳演算法和複雜適應系統的出現，並將它們融入他對智慧系統（包括自然系統和人工系統）如何運作的更廣闊的願景中。    讀ben chen 介紹的 文章《混沌的五十年》（Fifty Years of Chaos）是由「混沌理論」的奠基人之一、數學家詹姆士·約克（James Yorke）所寫。本文的四大核心重點分析：  1. 混沌的本質：完全決定論的系統，依然無法預測  2. 混沌不是特例，而是世界的常態  3. 三大限制原則與混沌的實際應用 4. 警示未來：人工智慧（AI）是當代的「新混沌」  

ai overview

赫伯特·西蒙是一位博學多才的諾貝爾獎得主，以其有限理性理論和人工智慧而聞名。他並非直接從事混沌理論的研究，而是為現代複雜性科學奠定了基礎，而複雜性科學又為混沌理論提供了概念架構。


西蒙的貢獻主要體現在以下三個方面：1. 《複雜性的架構》（1962）在其開創性論文《複雜性的架構》中，西蒙論證了複雜系統主要具有層級結構且近乎可分解。他提出，如果複雜系統（無論是在生物學、經濟學或組織學領域）是由穩定且半獨立的子系統所構成，那麼它們的演化速度就會更快。透過展示簡單的局部規則如何產生極其複雜且看似混沌的宏觀行為，他的工作預示並啟發了混沌理論後來研究的許多核心機制。 


2. 《人工科學》在其名著《人工科學》中，西蒙著重探討了複雜環境如何與簡單的人類決策相互作用。本書的後續版本直接探討了混沌理論、遺傳演算法和複雜適應系統的出現，並將它們融入他對智慧系統（包括自然系統和人工系統）如何運作的更廣闊的願景中。 



3. 有限理性與湧現混沌西蒙證明，由於時間、資訊和認知處理能力的限制，人類無法擁有完美的理性。人類並非追求“最大化”，而是傾向於選擇“足夠好”的選項。當成千上萬個有限理性個體在市場或組織中互動時，他們基於啟發式的個體決策往往會引發高度不可預測的非線性或混沌結果。


西蒙的人類問題解決模型為後來的複雜性經濟學家和社會科學家建構混沌社會經濟系統模型提供了微觀基礎。



如果您想了解西蒙建立的原則如何為現代混沌與系統科學鋪平道路，我可以：深入探討他在《複雜性的架構》中提出的兩個鐘錶匠的寓言；討論計算機模擬如何基於西蒙的概念對複雜自適應系統進行建模；將他的理論與現代行為經濟學和非線性動力學進行比較。請告訴我您想探索哪些領域！



Herbert Simon, the Nobel Prize-winning polymath known for bounded rationality and artificial intelligence, did not work directly within Chaos Theory. Instead, his work laid the foundational bedrock for modern complexity science, which provides the conceptual framework that encompasses chaos theory. [1, 2, 3, 4, 5]
Simon’s contributions directly intersect with chaos and complexity theory in three primary ways:
1. The Architecture of Complexity (1962)
In his seminal essay, "The Architecture of Complexity," Simon argued that complex systems are predominantly hierarchical and near-decomposable. [1, 2, 3]
  • He proposed that complex systems (whether in biology, economics, or organizations) evolve much faster if they are made up of stable, semi-independent subsystems. [1, 2, 3]
  • By demonstrating how simple, localized rules can generate deeply complex and seemingly chaotic macroscopic behaviors, his work anticipated and informed many of the core mechanisms later studied in chaos theory. [1]
2. The Sciences of the Artificial
In his famous book, The Sciences of the Artificial, Simon focused on how complex environments interact with simple human decision-making. Later editions of the book directly addressed the emergence of chaos theory, genetic algorithms, and complex adaptive systems, incorporating them into his broader vision of how intelligent systems—both natural and artificial—function. [1, 2]
3. Bounded Rationality and Emergent Chaos
Simon demonstrated that human beings are incapable of perfect rationality due to limitations in time, information, and cognitive processing power. Instead of "maximizing," humans satisfice—choosing options that are simply "good enough". [1, 2]
  • When thousands of boundedly rational agents interact within a market or organization, their individual, heuristic-based decisions can often trigger highly unpredictable, non-linear, or chaotic outcomes. [1]
  • Simon’s models of human problem-solving provided the micro-foundations used by later complexity economists and social scientists to model chaotic socio-economic systems. [1, 2]
If you are looking to explore how the principles Simon established paved the way for modern chaos and systems science, I can:
  • Provide a deeper look into his parable of the two watchmakers from "The Architecture of Complexity."
  • Discuss how computer simulations model complex adaptive systems based on Simon's concepts.
  • Compare his theories with modern behavioral economics and nonlinear dynamics. [1, 2]
Let me know which of these areas you would like to explore!




-----


這篇文章《混沌的五十年》（Fifty Years of Chaos）是由「混沌理論」的奠基人之一、數學家詹姆士·約克（James Yorke）所寫。他在文中回顧了自 1975 年與學生李天岩（T. Y. Li）共同發表著名論文《週期三即混沌》（Period 3 Implies Chaos）以來的這五十年，並探討了混沌現象在科學、歷史以及未來科技（特別是 AI）中的核心本質與應用。

以下為本文的四大核心重點分析：

### 1. 混沌的本質：完全決定論的系統，依然無法預測

約克指出，大眾常把「混沌」等同於隨機的雜訊，但數學上的混沌指的是：**即使一個系統的運行規則是完全確定的（Deterministic），它依然無法被精確預測。**

 * **對初始條件的敏感性（蝴蝶效應）：** 差之毫釐，失之千里。人類日常生活中充滿了這種因微小改變而導致巨大不同結果的「偶然性」。

 * **無法精確測量的現在：** 我們之所以無法預測遙遠的未來，是因為我們永遠無法百分之百精確地測量「現在」的狀態。即使把測量精確度提高到小數點後 300 位，微小的誤差隨著時間拉長依然會被無限放大。

### 2. 混沌不是特例，而是世界的常態

過去科學家為了找出漂亮、乾淨的線性解答（Linear solutions），習慣忽略現實中的雜質。但現實世界其实充满了解不開的「非線性」方程式。

 * 物理學家烏蘭（Stanislaw Ulam）曾敏銳地吐槽：「把混沌研究稱為『非線性科學』，就像把動物學稱為『非大象動物研究』一樣可笑。」因為非線性（混沌）才是世界的絕大多數。

 * 不過，混沌並非完全無跡可尋。它包含了**「奇異吸子」（Strange attractors）**——這是一種不斷創新、卻擁有固定輪廓的宏觀規律。這也是為什麼「超級預測員」能夠預測政治政變、或者馬克·吐溫會說「歷史不會重演，但總是押著相同的韻腳」。

### 3. 三大限制原則與混沌的實際應用

約克將**混沌（Chaos）**與海森堡的**不確定性原理（Uncertainty principle）**、哥德爾的**不完備定理（Incompleteness theorem）**並稱為「人類科學的三大限制原則」，它們共同界定了人類科學永遠無法跨越的認知邊界。

然而，這些限制定理反而大大推動了科技發展。過去五十年來，混沌理論已被廣泛應用於：

 * 電子電路與流體動力學

 * 流行病傳播模型（如 COVID-19 疫情預測）

 * 密碼學（利用混沌函數輸出看似隨機的結果來保障數位經濟安全）

### 4. 警示未來：人工智慧（AI）是當代的「新混沌」

約克將目前 AI（如大型語言模型 LLM）的崛起與混沌理論做出了深刻的連結與延伸：

 * **複雜度源於簡單規則：** AI 的本質是矩陣乘法，我們理解它的基本運算規則，卻無法理解它如何從中「湧現」出高階的自然語言。這就像我們知道大腦的生物定律，卻不明白大腦如何運作一樣。

 * **無法逆向工程的危險：** 人類總是「創造混沌容易，逆向工程（拆解並理解）混沌困難」。AI 的發展軌跡與天氣預報極為相似，正因為我們不完全懂現在的 AI，我們就無法預測它未來的行為。這對人類而言是一個高風險的未知數。

### 💡 總結作者的智慧點評

約克在文章尾聲勉勵後進，研究應該**「從簡單的問題著手」**，因為簡單的問題在深入後往往會變得比預期更難；如果一開始就挑戰明顯困難的問題，最後只會流於無解。

他與李天岩並未「發明」混沌，他們只是在數學與日常生活之間搭建了一座橋樑，並且幸運地挑選了一個極具傳播力的好名字——**「混沌（Chaos）」

張貼者： 於 沒有留言:

2026年6月6日 星期六

紀念 H. A. SIMON( 2026 6月15) 題目：淵博人生敘述學與人工科學，從SIMOＮ的回憶錄《我生的諸模式》 代表作《人工科學》生命學問的完成，或許可稱之為＂淵博人生敘述學與人工科學＂。Nobel Prize laureate Demis Hassabis was awarded the Nobel Prize for using AI to predict the structure of proteins. For him, AI is a tool that will help scientists make even more discoveries in the years to come. Hassabis took part in our Nobel Prize Dialogue ‘The Future of Science With AI’ which discussed how AI might transform science in the future. 讀＂游珮芸的一千零一頁 《從《茉莉人生》到《來自清水的孩子》》出發．．．．．．．《茉莉人生》《Ｓ，我的父親說．．．．．．》（ＧＩＰＩ/GIPI 作，倪安宇翻譯，台北:無限，2013）．．．．． 。迷宮-追尋-決策 ：「我們身後能留下的，唯有愛。」Herbert A. Simon先生紀念 (2026 0615；1 《紐約時報》，《明周文化 MP Weekly 明報周刊文化 ) 村上春樹的短篇小說〈四月某個晴朗的早晨遇見100%的女孩〉（收錄於同名短篇小說集《遇見100%的女孩》中）。：很簡單地說，人生的決策準則是「滿意」（他創英文新字），非最佳或極值…..。 我們每一人都有一套價值與哲學，Simon 選擇四十幾年每天步行來回學校，吃穿等到極簡單，多發表各領域的深入論文，課程創新 紀念5 從MIT公開下載的書： Scientific Discovery: Computational Explorations of the Creative ProcessUnavailable By Patrick W. Langley, Herbert A. Simon, Gary Bradshaw, Jan M. Zytkow 到 2026年5月18 " //今天 Google IO 活動同步發表了兩篇 Nature 論文，值得學研界朋友關注"

紀念  H. A. SIMON( 2026 6月15) 題目：淵博人生敘述學與人工科學，從SIMOＮ的回憶錄《我生的諸模式》 代表作《人工科學》生命學問的完成，或許可稱之為＂淵博人生敘述學與人工科學＂。Nobel Prize laureate Demis Hassabis was awarded the Nobel Prize for using AI to predict the structure of proteins. For him, AI is a tool that will help scientists make even more discoveries in the years to come.     Hassabis took part in our Nobel Prize Dialogue ‘The Future of Science With AI’ which discussed how AI might transform science in the future.      讀＂游珮芸的一千零一頁 《從《茉莉人生》到《來自清水的孩子》》出發．．．．．．．《茉莉人生》《Ｓ，我的父親說．．．．．．》（ＧＩＰＩ/GIPI 作，倪安宇翻譯，台北:無限，2013）．．．．．  。迷宮-追尋-決策   ：「我們身後能留下的，唯有愛。」Herbert A. Simon先生紀念 (2026 0615；1  《紐約時報》，《明周文化 MP Weekly  明報周刊文化 ) 村上春樹的短篇小說〈四月某個晴朗的早晨遇見100%的女孩〉（收錄於同名短篇小說集《遇見100%的女孩》中）。：很簡單地說，人生的決策準則是「滿意」（他創英文新字），非最佳或極值…..。 我們每一人都有一套價值與哲學，Simon 選擇四十幾年每天步行來回學校，吃穿等到極簡單，多發表各領域的深入論文，課程創新      紀念5    從MIT公開下載的書： Scientific Discovery: Computational Explorations of the Creative ProcessUnavailable By Patrick W. Langley, Herbert A. Simon, Gary Bradshaw, Jan M. Zytkow  到 2026年5月18 " //今天 Google IO 活動同步發表了兩篇 Nature 論文，值得學研界朋友關注"

初次翻 Martin Greenberg英譯本2013：    Faust: A Tragedy, Parts One and Two, Fully Revised by Johann Wolfgang von Goethe (Author),   三感想： 歌德的Dedication 初的迷宮  "...I retrace life's labyrinthine..."  VS MODELS OF MY LIFE. 第2衝擊  ：  The exact phrase "In the beginning was the Deed" comes from Johann Wolfgang von Goethe's classic play, Faust. In the famous "Study" scene, the protagonist, Faust, struggles to translate the opening line of the Gospel of John ("In the beginning was the Word") into German and ultimately decides that "Deed" (Tat) is the most meaningful starting point for human existence.  封底摘錄 H. BLOOM 的書評關於 CANON 詩歌的六面？考量 (翻譯))


“In the next 10 years we are going to be entering what I feel like is a new renaissance.”

 

Nobel Prize laureate Demis Hassabis was awarded the Nobel Prize for using AI to predict the structure of proteins. For him, AI is a tool that will help scientists make even more discoveries in the years to come.

 

Hassabis took part in our Nobel Prize Dialogue ‘The Future of Science With AI’ which discussed how AI might transform science in the future.

 

Watch the full event at https://www.nobelprize.org/events/nobel-prize-dialogue/london-2026/



紀念  H. A. SIMON( 2026 6月15) 題目：淵博人生敘述學與人工科學，從SIMOＮ的回憶錄《我生的諸模式》 代表作《人工科學》生命學問的完成，或許可稱之為＂淵博人生敘述學與人工科學＂，讀＂游珮芸的一千零一頁 《從《茉莉人生》到《來自清水的孩子》》出發．．．．．．．《茉莉人生》《Ｓ，我的父親說．．．．．．》（ＧＩＰＩ/GIPI 作，倪安宇翻譯，台北:無限，2013）．．．．．  。迷宮-追尋-決策   ：「我們身後能留下的，唯有愛。」


這是篇有趣有用的文章,值得教育界重視. 即深入了解漫畫，動畫，圖像小說，

Ｓ，我的父親說．．．．．．

AI科技，整合。當然,題材，我們的故事等，同樣重要。譬如東海傑出校友周教授有「文學工廠」，有創意學院的「音樂劇」，有高唱「AI pc 教室」，只是散發出來的宣傳，成果還差得很遠.





紀念 H A SIMON 2026 (0)：

 能用它來談2026年的 AI 嗎：某 AI 大師譚 讓‧皮亞傑的一句話："Intelligence is not what you know, it's what you do when you don't know"  約翰·霍爾特在1964年出版的一本書中對其進行了重新表述並使其廣為人知：“智力的真正考驗不在於我們知道多少，而在於當我們不知道該做什麼時，我們的行      



我想起了發展心理學先驅讓‧皮亞傑一句精彩卻又似曾相識的名言：


“L'intelligence, ce n'est pas ce que l'on sait, mais ce que l'on fait quand on ne sait pas.”


“智力不是你知道什麼，而是當你不知道時你做什麼。”


顯然，這並非皮亞傑的原話，而是他對這主題觀點的總結。心理學家約翰·霍爾特在1964年出版的一本書中對其進行了重新表述並使其廣為人知：“智力的真正考驗不在於我們知道多少，而在於當我們不知道該做什麼時，我們的行為方式。”


這些簡單的引言闡明了當今人工智慧領域的許多問題：


- 為什麼累積陳述性知識看似智力，但其實並非智力？


- 為什麼累積技能看似智力，但其實並非智力？


- 為什麼無需事先訓練就能「零基礎」解決新問題的能力是衡量智力的重要指標？


- 為什麼智力並非一系列後天習得的技能，而是無需或只需極少訓練就能快速掌握新技能的能力？


我們對現實的認知模型使我們能夠預測自身行為的後果，從而具備規劃能力，最終使我們能夠在無需事先訓練的情況下理解和應對新情況。

I was reminded of this wonderful, yet apocryphal, quote by developmental psychology pioneer Jean Piaget:

"L'intelligence, ce n'est pas ce que l'on sait, mais ce que l'on fait quand on ne sait pas." 

"Intelligence is not what you know, it's what you do when you don't know"


Apparently this is not a real quote but a synthesis of Piaget's positions on the topic. Psychologist John Holt reformulated and popularized it in a 1964 book: "The true test of intelligence is not how much we know how to do, but how we behave when we don't know what to do." 


These simple quotes clarify many questions surrounding AI today: 

- Why the accumulation of declarative knowledge seems like Intelligence but is not intelligence.

- Why the accumulation of skills seems like intelligence but is not intelligence.

- Why the ability to solve new problems "zero shot" without prior training on said problem is an important metric of intelligence.

- Why intelligence is not a collection of learned skills but an ability to acquire new skills very quickly, with very little or no training.


Our mental model of reality gives us the ability to predict the consequences of our actions, which gives us the ability to plan, which gives us the ability to apprehend new situations without prior training

 



AI Overview


是的，黃仁勳在卡內基美隆大學（CMU）2026屆畢業典禮的演講中，確實提到了該校在機器人與人工智慧領域的先驅歷史。 [1]
他特別指出，CMU 是人工智慧與機器人技術的發源地之一，並提到了該校在1979年成立了著名的機器人研究所（Robotics Institute），這項成就鞏固了 CMU 在技術創新與前沿科技發展中的歷史地位。 [1]
在這場以「智慧普及化將重塑每個人」為核心的演講中，黃仁勳回顧了從1950年代的 AI 先驅學者（如 Allen Newell 和 Herbert Simon）到1979年成立機器人研究所，強調 CMU 數十年來始終處於技術革命的最前線。 [1]
您可以透過 卡內基美隆大學官方 YouTube 頻道 觀看完整的畢業典禮致詞影片，深入了解他對 AI 時代未來人才與產業發展的見解。 [1, 2, 3]


AI OVERVIEW： 黃仁勳在卡內基美隆大學（CMU）2026屆畢業典禮演講中，強調CMU是人工智慧（AI）真正的發源地之一。他指出，該校研究人員在1950年代發明了史上第一個AI電腦程式「邏輯理論家」（Logic Theorist）。「邏輯理論家」是由CMU的艾倫·紐厄爾（Allen Newell）、司馬賀（Herbert A. Simon，後獲諾貝爾獎）與約翰·克里夫·肖（J. C. Shaw）於1955年與1956年間共同開發。這個程式被廣泛認為是歷史上第一個能自動進行符號推理與解決問題的AI程式。它成功證明了數學巨著《數學原理》（Principia Mathematica）中的多個定理，甚至找出了比原著更簡練的證明方法。這段歷史象徵了AI發展的開端，也呼應了黃仁勳在演講中鼓勵畢業生，在這個由AI重塑運算的新時代中「親手創造未來」的期許。

 

Herbert A. Simon先生紀念 (2026 0615；1  《紐約時報》，《明周文化 MP Weekly  明報周刊文化 ) 村上春樹的短篇小說〈四月某個晴朗的早晨遇見100%的女孩〉（收錄於同名短篇小說集《遇見100%的女孩》中）。：很簡單地說，人生的決策準則是「滿意」（他創英文新字），非最佳或極值…..。 我們每一人都有一套價值與哲學，Simon 選擇四十幾年每天步行來回學校，吃穿等到極簡單，多發表各領域的深入論文，課程創新


AI Overview
這部作品是村上春樹的短篇小說〈四月某個晴朗的早晨遇見100%的女孩〉（收錄於同名短篇小說集《遇見100%的女孩》中）。
故事中描述男女主角在東京原宿的後街擦身而過，男主角回憶起這段往事時，寫下了這段經典的句子：「她從東邊往西邊走，我從西邊往東邊走。真是一個非常舒服的四月的早晨。」
您可以透過 博客來 了解更多關於這本經典短篇集的資訊。



------

我們前天在關於黃仁勳在CMU 畢業典禮演講，談到我的英雄/筆友 Simon,沒想到隔一天在紐約時報就有這篇。其實這篇文章還提到許多其他故事,如村上的短篇小說，譬如說，大學有兩位戀人，相信如果「真佳偶」，畢業後各自從東與西去「找」，最終一定會重逢的……
很簡單地說，人生的決策準則是「滿意」（他創英文新字），非最佳或極值…..。
我們每一人都有一套價值與哲學，Simon 選擇四十幾年每天步行來回學校，吃穿等到極簡單，多發表各領域的深入論文，課程創新，如法國革命中的決策論等等。
或許找時間將此篇剪貼在此寶地。

明周文化 MP Weekly 

孤獨的少年少女在街角偶遇，直覺認定彼此是天作之合——這簡直是奇蹟般的相遇。他們牽着手，暢談數小時。一絲疑慮突然在腦海浮現：「夢想這麼輕易就成真，真的好嗎？」於是，二人決定考驗這段關係：若真是天作之合，即使分開，也必能重逢，到時便可確信。少年向西走，少女向東走。他們確實是天作之合。多年後，兩人在街頭擦肩而過，但記憶已經模糊。最終，二人沒有重逢。
做決策時，如果你總是追求「最好」，恐怕很難感到幸福。
身處資訊泛濫、選擇繁多的時代，我們以為只要拚命尋找，就一定能找到萬中無一的選項。現代香港人會稱之為「選擇困難症」或「完美主義」，心理學家則稱之為「最優主義」（tendency maximizing）。
大多數人都忽略了，「搜尋」本身也是一種成本，如果你把這點納入考慮，就會發現：最好的策略，恰恰不在於追求最好。
人工智能與認知心理學先驅、諾貝爾經濟學獎得主 Herbert Simon 做決策時，會考慮若干選項，偶爾請教他人，選定之後便向前走。他不苦惱，也不後悔。（The best is enemy of the good）是他的座右銘。
他的女兒憶述：父親為免每天挑選顏色款式，只穿同一品牌的襪子；同時只擁有一頂黑色貝雷帽。
以上為文章節錄，完整文章於《明周文化》網站：https://mpweekly.hk/kB3LY
顯示較少




The Nobel-Winning Psychologist Who Believed He Found the Secret to Happiness
May 12, 2026
A peach balancing on top of another peach, against a dark background.
Credit...Daniel Ribar
Listen · 7:03 min
Share full article528
By David Epstein
Mr. Epstein is the author of “Inside the Box: How Constraints Make Us Better.”
If in making decisions you are often guided by a search for the best, you are going about decision making all wrong — and you’re also probably less happy for it.
In an age of information and choice abundance, we assume we can find the best of everything if we look long and hard enough. Psychologists call that tendency maximizing.
But searching for the best is the wrong goal. That is because searching is itself a cost, and most people forget to account for it. If you did, you would see that the optimal strategy isn’t optimizing at all.
There’s a better way to make decisions. To understand it, you should know about Herbert Simon, a pioneer of artificial intelligence and cognitive psychology, as well as a Nobel laureate in economics. Mr. Simon demonstrated that for most decisions, humans can’t really evaluate the options available — there are too many, our information about them is incomplete and our minds aren’t built to weigh them all — and so we rely on mental shortcuts. He coined the term “satisficing” — a portmanteau of satisfy and suffice — to describe how we consider a limited set of options, then choose one that is good enough and move on to live our lives.
Sign up for the Opinion Today newsletter Get expert analysis of the news and a guide to the big ideas shaping the world every weekday morning. Get it sent to your inbox.
When Mr. Simon faced a decision, he considered a few alternatives, sometimes asked for advice, chose and moved on. He didn’t agonize, and he didn’t second-guess. “The best is enemy of the good” was the mantra he lived by.
Mr. Simon was, as he put it, an “incorrigible satisficer.” His eldest daughter, Katherine, recalled that he wore one brand of socks to avoid selecting color or style each morning, and he owned exactly one black beret at a time, made at a particular haberdashery in Europe.
According to Katherine, he said that one needed only three sets of clothes: “one on one’s body, one in the wash and one in the closet ready to wear.” He always ate the same breakfast — oatmeal, half a grapefruit, black coffee — and lived in the same house for 46 years.
“My father simplified his life in terms of his daily habits,” Katherine wrote, “thus eliminating the need to make little decisions about everything.” By taking the small decisions off his plate, that simplification freed his attention for the people and work that actually mattered to him. The mathematician John Allen Paulos illustrated the same principle with a thought experiment in his 1988 book “Innumeracy”: How should you choose your final romantic partner? First, he argued, you should estimate the number of people you might plausibly date in your lifetime. Then date roughly the first third with no intention of committing. Use that time purely to calibrate what you liked, what you didn’t like and what you might be missing.
After that, commit to the very next person you like better than everyone you’ve already dated. Mr. Paulos was illustrating a well-known result in probability, which shows that this rule gives you the best chance of ending up with the best partner in the whole sequence. Keep pushing past that point, and you’re more likely to end up with a worse match or no one at all. The core insight — that the path to the best outcome runs directly through the willingness to stop searching long before you’ve exhausted the options — extends far beyond dating.
Psychologists who followed up on Mr. Simon’s work have shown that his personal philosophy was both efficient and wise. Shortly after Mr. Simon’s death in 2001, a team of researchers created a maximization scale to measure where a person falls on the spectrum between maximizer and satisficer. They found that it’s usually bad to be a maximizer.
Maximizers tend to be less satisfied with their decisions and their lives. They are typically less happy, more prone to regret and more likely to compare themselves endlessly with others. Satisficers don’t necessarily have low standards. Their standard is “good enough for me” rather than “the best out there,” and that makes it possible to feel satisfied with their choices, instead of haunted by the ones they didn’t make.
The psychologist Mihaly Csikszentmihalyi, who first used the term “flow” to describe states of complete absorption in an activity, put it well. By making up one’s mind to invest in a choice, regardless of more attractive options that may come along later, “a great deal of energy gets freed up for living, instead of being spent on wondering about how to live.”
Advertisement This is critical today because chronic maximizing has never been easier. In 2006 an economist calculated that the consumer options available to citizens of modern economies exceeded those of preindustrial societies roughly by a factor of 100 million. That is an almost incomprehensible multiplication of choice, and it extends well beyond consumer goods into questions of who to be, how to live, where to work and whom to love.
Social media has intensified the problem by functioning as an infinite comparison engine. When you can see a curated highlight reel of everyone else’s career, relationship, home and vacation, the very concept of “good enough” begins to feel like settling.
The pull to keep searching for something better has poisoned even the most mundane moments. Research shows that giving viewers many videos to flip between makes them more bored than if they focus on just one. One way to interpret the findings is that the mere notion that something better might be out there spoils the moment.
Studies in the United States and China show that since about 2010, young people have reported becoming increasingly bored. Dating apps have offered a version of Mr. Paulos’s thought experiment, with users forever wondering what might be beyond that next swipe — maximizing in its purest form.
And now artificial intelligence promises to help us optimize everything: our schedules, our diets, our wardrobes, our creative output. If Mr. Simon was right, the hidden danger of these tools is that they will expand the menu of options and comparisons even further. The Japanese novelist Haruki Murakami captured the maximizer’s tragedy in a short story. A lonely boy and girl meet on a street corner and intuitively recognize that they are the perfect match for each other. It’s a miracle. They hold hands and talk for hours. But then a sliver of doubt creeps in: “Was it really all right for one’s dreams to come true so easily?” They decide on a test. If they truly are perfect for each other, they can part and will inevitably meet again. Then they’ll know for sure. The boy walks off to the west, and the girl to the east. They really were perfect for each other. Years later, they pass in the street, but their memories have faded. They never meet again.
Mr. Simon would not have been surprised they never met again. Whether you’re searching for a dishwasher or a date, set a good-enough standard. Stop when it’s met. Save your cognitive resources for things that matter.
David Epstein is the author of, most recently, “Inside the Box: How Constraints Make Us Better” and “Range: Why Generalists Triumph in a Specialized World.”
The Times is committed to publishing a diversity of letters to the editor. We’d like to hear what you think about this or any of our articles. Here are some tips. And here’s our email: letters@nytimes.com.
Follow the New York Times Opinion section on Facebook, Instagram, TikTok, Bluesky, WhatsApp and Threads.



++++++

 

Herbert A. Simon先生紀念5    從MIT公開下載的書： Scientific Discovery: Computational Explorations of the Creative ProcessUnavailable By Patrick W. Langley, Herbert A. Simon, Gary Bradshaw, Jan M. Zytkow  到 2026年5月18 " //今天 Google IO 活動同步發表了兩篇 Nature 論文，值得學研界朋友關注"

Book cover for Scientific Discovery: Computational Explorations of the Creative Process

Scientific Discovery: Computational Explorations of the Creative ProcessUnavailable

By
 
Patrick W. Langley
 
Herbert A. Simon
 
Gary Bradshaw
 
Jan M. Zytkow
The MIT Press
DOI:
 
https://doi.org/10.7551/mitpress/6090.001.0001
ISBN electronic:
 
9780262316002
In Special Collection: CogNet
Publication date:
 
1987

Scientific discovery is often regarded as romantic and creative—and hence unanalyzable—whereas the everyday process of verifying discoveries is sober and more suited to analysis. Yet this fascinating exploration of how scientific work proceeds argues that however sudden the moment of discovery may seem, the discovery process can be described and modeled.

Using the methods and concepts of contemporary information-processing psychology (or cognitive science) the authors develop a series of artificial-intelligence programs that can simulate the human thought processes used to discover scientific laws. The programs—BACON, DALTON, GLAUBER, and STAHL—are all largely data-driven, that is, when presented with series of chemical or physical measurements they search for uniformities and linking elements, generating and checking hypotheses and creating new concepts as they go along.

Scientific Discovery examines the nature of scientific research and reviews the arguments for and against a normative theory of discovery; describes the evolution of the BACON programs, which discover quantitative empirical laws and invent new concepts; presents programs that discover laws in qualitative and quantitative data; and ties the results together, suggesting how a combined and extended program might find research problems, invent new instruments, and invent appropriate problem representations. Numerous prominent historical examples of discoveries from physics and chemistry are used as tests for the programs and anchor the discussion concretely in the history of science.


Table of Contents




//今天 Google IO 活動同步發表了兩篇 Nature 論文，值得學研界朋友關注：


- Gottweis, J., Weng, WH., Daryin, A. et al. Accelerating scientific discovery with Co-Scientist. Nature (2026). https://doi.org/10.1038/s41586-026-10644-y


這篇發表於《自然》的論文介紹了 Google 團隊開發的 Co-Scientist。這是一個基於 Gemini 的多代理 AI 系統，由生成、反思、排名、演化、鄰近和元審查六個專業代理組成。不同於傳統工具，它能在非同步框架內透過錦標賽制的演化過程與自我對弈辯論，生成前所未有、可證實的新穎科學假說，且其假說品質隨測試時計算量的增加而持續提升，未見飽和。


Co-Scientist 在生物醫學領域展現出強大實力：在白血病藥物重定向測試中，系統建議的藥物有三種經體外實驗證實能抑制細胞存活；它甚至獨立提出 cf-PICI 擴展宿主範圍的假說，與研究組尚未發表的實驗發現完全吻合。在 15 個研究目標的專家評估中，Co-Scientist 的假說水準成功超越了 Gemini 2.0 Pro、GPT-4o、OpenAI o1/o3-mini 及 DeepSeek R1 等前沿模型。


- Aygün, E., Belyaeva, A., Comanici, G. et al. An AI system to help scientists write expert-level empirical software. Nature (2026). https://doi.org/10.1038/s41586-026-10658-6


這篇發表於《自然》的論文介紹了 Google 團隊開發的 ERA（實證研究助理）。這是一個將大型語言模型與樹狀搜索結合的代理 AI 系統，能自主生成、測試並迭代改進科學軟體，有效解決了過去需要專家花費數年勞動才能創建特定領域軟體的瓶頸。


ERA 的核心機制是透過大型語言模型改寫代碼以提升可量化指標，並利用樹狀搜索引導探索與回溯。該系統在六個科學基準測試中達到專家級水準：在單細胞 RNA 測序分析中，其生成的方法超越了公開排行榜上的既有做法；在 COVID-19 預測上，也擊敗了美國 CDC 的集成模型。研究更發現，ERA 有能力透過重組現有演算法來開創全新策略。這項突破展示了 AI 在多個高風險領域同時創建科學軟體的能力，也引發了未來如何部署與治理這類系統的深遠討論。//





張貼者： 於 沒有留言:
訂閱： 文章 (Atom)