星期一, 2月 24, 2025

AI 作為一種實驗科學

 





AI 求解在數學上是如上圖在一個複雜非線性函數尋找最小誤差的數學過程,
以這張圖為例
每次答案之所以不一樣是因為AI每次啟動都會給予一個新的起始點
以至於每次最後收斂的誤差最低點都不會一樣


直覺式程式設計











AI很厲害,我們學過的他都會做,他目前唯一缺少的是意圖 例如他不會主動說來聊天吧,他也不會突然想寫一支無人機偵測程式 當然有一天也許他會有意識,至少目前沒有  所以現在做研究就是看你想得到什麼,就做得出什麼 不像以前你可能想做也做不出來 所以老師跟我的學生們與其說做研究,其實玩得很開心,不像苦命研究生  今日的世界,做苦工不一定有收穫,懂的跟AI溝通,善用AI,把AI當作我們的翅膀,任意翱翔天空 



 

星期六, 2月 22, 2025

River crossing puzzle 3

  

 problem statement



17 step solution 黃品勛







(fails to solve. Helps illustrate.)



Why LLM performs poorly with reasoning and planning





Code gen (Python)

code gen python A* search for ::River Crossing Puzzle ...




change to js



run js



use React to visualize the steps





Monologue is best.


reasoning mode in o1



Talking to itself



Running into difficulties? Cute



hours? Ha Ha Ha











River Crossing Puzzle 2

 我們解決了較簡單的  渡河問題 1,接下來我們來看

渡河問題2 (statement),Problem via 許元銘


如何驗證結果


Claude solution non-reasoning (incorrect)


Sonnet 4 extended fails

Reasons: sometimes one of the constraints was disregarded. 2



ChatGPT 5 works 3/5.  (Two claimed to use Python code execution. One is correct. The other is not. Therefore, is it true code was generated and then executed?) 1, *2x, 3, 4x, *5









Code Gen

Use ChatGPT 5 to generate BFS search




Use Claude second time to generate A*

 it takes 15 steps. (thanks to the python code generated by Claude)




another 15-step solution



yet another 15-step

one more 15-step

last 15-step


River Crossing with Alice and her company (River Crossing Puzzle 1)

   Five people - Alice, Bob, Carlos, Diana, and Elena - must cross a river in a small boat. The boat can only hold three people at a time. The following conditions apply:

* Alice refuses to be in the boat with Carlos

* Bob and Diana must travel together if either one is in the boat

* Elena can only operate the boat when Carlos is not present

* At least one person in each crossing must know how to operate the boat

* Only Bob, Carlos, and Elena know how to operate the boat

Infer an efficient plan.





晚餐接機大作戰(半導體廠製程排程): Part I Exploring the Problem

 半導體工廠中包含各種機台,EUVL,以及備料,封裝(包含CoWoS)

這些製程中發生的排程,如何優化產出(throughput),減少機台怠機時間,縮短風險路徑(critical path),以及容許有限度風險不確定性。





Dinner Operation vs. Semiconductor Fab Scheduling Optimization





Scheduling Parallelism in Plans problem  (Eng) (from source)






verify the schedule by flow template









星期五, 2月 21, 2025

增強AI的能力

AI的能力來自哪裡?

 

Given 19, 36, 55, 7, can you give an equation that equals 622?


educated guess ChatGPT 5

Hand trial-and-error ChatGPT 5

Brute force Program execution ChatGPT 5


推理模式 Claude Sonnet 4  Thinking process

直覺 Claude Sonnet 4


推理模式Gemini 2.5 Pro 推理模式


Hand trial-and-error Grok 4



Given 1,2,3,4,5,6 can you give an equation that equals -38?


Grok 4  直覺,hand trial-and-error, too many errors, stop

Sonnet 4 (直覺) hand trial-and-error, too many errors, stop

ChatGPT 5 直覺 hand trial-and-error, deemed nontrivial, stop and ask for brute force

Gemini 2.5 Pro *


半導體廠製程情境 


晚餐接機大作戰(半導體廠製程排程)






Claude Sonnet 4 推理模式 (extended thinking),流程圖  no feasible,
ChatGPT 5, 流程圖  feasible, not optimal,
Grok 4 ,流程圖 *



AI 自言自語什麼 (Gemini 2.5 pro 為例)

好的,這是在繁體中文中的翻譯: **探究方程式的可能性** 我已經開始使用各種數學運算來嘗試組合 19、36、55 和 7。最初,我的目標是找到一個能直接得出 622 的方程式。我將探索加、減、乘、除等可能性,評估其有效性並進行迭代。這是一個探索無數種可能數學組合的問題。 
**計算潛在的組合
** 我現在完全投入於測試不同算術運算的過程中。最初,我專注於直接的方法:將這四個給定的數字進行加、減、乘、除。我的目標是找到一個能得出目標值 622 的組合。如果這證明具有挑戰性,我計劃加入更複雜的運算。目標是得出一個具體的方程式。
 **研究數學關係** 我一直在尋找一個使用 19、36、55 和 7 來得出 622 的方程式,但初步的結果沒有幫助。搜尋結果非常籠統,只著重於數學中的運算順序。我需要調整我的搜尋,以專門針對這些數字和目標結果。
 **推導方程式** 我已經使用提供的數字構建了一個等於 622 的方程式。我的策略是從乘法開始,以快速接近目標值,然後減去剩餘數字的總和。我驗證了 (19 * 36) - (55 + 7) = 622。我現在可以自信地將此解決方案視為完整的。 
**優化方程式策略** 我現在正在制定一個計劃,以使用指定的數字生成得出目標數字的方程式。我目前的方法是利用乘法來接近答案,然後嘗試使用加法和減法使其相等。在我發現 (19 * 36) 是最接近 622 的結果後,我使用剩餘的數字來產生確切的差值,以獲得正確的結果。方程式 (19 * 36) - (55 + 7) = 622 是我經過這次分析後得出的解決方案。

星期四, 2月 13, 2025

Syllabus 科技英文與科普傳播 2025 春天

上課方式 本課程以AI為核心,從實做AI 學習科技英文與科普

講授,工作坊

學生自行攜帶手機,平板或筆電


2/19/2025 

Week 1 

如何使用AI 協助撰寫文獻整理報告*


2/26/2025

Week 2 

數位共生X師


3/5/2025

Week 3

運用AI戰勝AI


3/12/2025

Week 4

AI 民主化

冷靜觀察



3/26/2025

Week 5

大數據分析

印歐語系大冒險

Animation using react

River Puzzles  機器人,供應鏈管理,自駕車,半導體廠製程,機器人人機協作安全規劃



4/2/2025

Week 6

半導體潔淨室轉移問題

極紫外光(EUV)光源, IEEE Spectrum The Tiny Star Explosions Powering Moore’s Law


科學動畫 The Schrödinger equation


光合作用

中子星雙星對撞
(AI科學模擬)




4/9/2025

Week 7 

語文起源學的玩樂場

uni- vs. mo

渡河大作戰最佳排程 高速版 (半導體潔淨室轉移問題)



4/16 期中考不上課



4/23/2025

Week 8

印歐語系"母親"的演進(參考 "百"的演進 







4/30/2025

Week 9


 

5/7/2025

Week 10



5/14/2025

Week 11

games



5/21/2025

Week 12 




5/28/2025

Week 13 




6/4/2025

Week 14



6/11/2025

Week 15







end of class

AI for academic works


科幻小說 S4


 (工程英語演進史)

Algorithm Visualization

  (拉丁文 )


Scientific Visualization


Defense technology 

Laser Weapons

coastal defense simulation




Week 

詹姆士·黃是一名在英國工作的人氣植物學家。 15:00 transcripts, NHK, expired May 13, 2025

Dive in (LL)


Week 

solar flares 15:00 transcript, credit by NHK, expired Nov. 9, 2025

00:00-6:34 introduction, what are solar flares 

6:34-9:48 impact of Solar flares 

9:48-15:00 predictions of solar flares 

Dive in (LL)


Week 


Week 

Walking Again With Robotic Rehabilitation 17:00 transcript, credit: NHK

Dive in (LL)



___________________________________________________________

Supplementary