2026年9月30日 星期三

EX# Scan to Grade

Grade EX#2 in Gmail

  • in gmail, grade in depth EX#2
  • positive tone, bilingual, english first
  • mark graded by Claude Assistant
  • compose reply in the same thread rather than an independent mail
  • do not send, wait for my confirmation

try the ones with unopened attachments or Artifact-only links. also try the ones with Artifact-only links

Assignment

EX#2 is handed out at the blogspot https://minstral.blogspot.com/2026/09/ex2-ai-for-electronics.html

Scan for new batches

scan for new incoming batch which may be round 2 or higher with added works done. skip it if labeled 退件

2026年9月22日 星期二

cv review

Review goal

check for any possibilities of improvement, more targeted, more convincing, more impreesive

Input

for 考生資料表.pdf or something similar

Follow-up

go 如果你需要,我可以把上述建議整理成一份可對照原文逐段修改的 Word 檔(甚至直接在原始 docx 上加註解/追蹤修訂),方便直接交給學生對照修改,要我做嗎?

有利文件

  • 缺少摘要
  • 需要一頁開門見山
  • 讓人覺得非要選你不可

2026年9月19日 星期六

EX#1

【EX#1 繳交方式與時程】

繳交請寄到 chang212@gmail.com,主旨請照以下格式:

EX#1 [學號] [姓名]

時程分兩階段——當天下午 3:00 下課前先寄草稿,進度不拘,只做了十分之一也沒關係;完稿則請在本週六 23:59 前寄出。

草稿的用意是確認大家有開始動手,不作為評分依據,所以不必等做完才交。下次起,未按時繳交草稿者,該次作業扣 40%。

作業規定 Content share policy

作業規定全文:https://minstral.blogspot.com/2026/09/ex1-english-is-your-programming-language.html

  • Share only link, pure text, or markdown (md).
  • No attachments accepted: no html, screen dump, or png.
  • Non-compliant homework will be rejected and returned to you.

連結部分將進行計分批改;附件部分,不予評閱。

如何分享你的作品 How to share your work

To share your work, refer to the following. If a link fails, check its sharing authorization.

Overcome rendering issues

  1. Copy the html code generated by xxx.
  2. Paste the code to Claude.
  3. Prompt with "output as artifact html".
  4. Share the artifact.
  5. Copy the URL link and send it to me.

正確做法(謝同學提供)

Prob 2.

後續作業與退件

後續作業請在這裡繳交(同一個討論串),以利批閱計分。不要另起新的 email,請回到之前同一個討論串。

退件:Your homework assignment needs rework. It does not meet the standard of this assignment.

Your homework flags a serious issue. You did not think at all. You just outsource everything to AI. When AI makes mistakes, you are not aware of it. You do not even push back and check.

At the end of the day, very little is learned.

Try to cowork with AI rather than delegate everything to it.

Working prompts

  • Scan for new incoming batches, which may be round 2 or higher with added work done. Skip any labeled 退件.
  • Ex 1 [11426XXX] is running into persistent issues. Help him overcome them and draft a reply.
  • Is it scientifically faithful and accurate?