張耀仁: 2月 2025

星期四, 2月 27, 2025

運用AI戰勝AI

讓我們在仔細回顧一下

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

晚餐接機大作戰(半導體廠製程排程)

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

artifact

出處

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

17 step solution 王智弘

Use react to illustrate the process

(fails to solve. Helps illustrate.)

even 3.7 Extended mode struggles

Why LLM performs poorly with reasoning and planning

Code gen (Python)

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

Python on colab

Use REACT to visualize the steps

change to js

run js

use React to visualize the steps

I really like ChatGPT o1 reasoning performance.

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

Visualization to verify results

Claude solution non-reasoning (incorrect)

Sonnet 4 extended fails

Reasons: sometimes one of the constraints was disregarded.

ChatGPT o1 solution 1

backtracking observed
cannot work independently
some human corrections required
overall, it is helpful

ChatGPT fails (4o or o1)

one invalid case

(use Claude to visualize the issue or debug)

Grok

Even reasoning mode of Grok fails.

Code Gen

Use ChatGPT o1 to generate A* search

4o fails to generate A* search that works

Use Claude second time to generate A*

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

python code

another 15-step solution

yet another 15-step

one more 15-step

last 15-step

心得

打開Sonnet 3.7推理模式

我目前還沒有辦法完全正確渡河

最好的一次用了2:57，錯在第12步，不過是個小失誤，不花腦筋很容易改

至於跑到耗盡token那次4:47，居然沒有給出答案

Sonnet 4 still didn’t get it, either.

可以這麼說，這題渡河用 python 寫 A*

可以找到最佳解 15 步

我目前使用所有 no code 方式，無論 ChatGPT, grok, Claude 各種推理模式，沒有一次能得到完美無瑕的解

渡河大作戰最佳排程高速版，AI 推理約需3-10分鐘，用AI生成Python程式，可加快執行速度到千分之一秒以下。可以參考 Use Code Gen to solve River Puzzle 2 ，結果必須視覺化，動畫尤佳

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.