2026年10月25日 星期日

2026年10月23日 星期五

HW#6

 is it scientifically faithful and accurate?

is it research grade?
Make it highly accomplished

2026年10月18日 星期日

EX#5/HW#5

Overall

Comprehensive.

Strength: kept every failed target visible, traced the routability failure to its real cause yourself, and stated clearly what your model can and cannot support.

Core areas of improvement

  • staircase problem in routing
  • resistor/capacitor/transistor geometry is incorrect.
  • devices lack halos
  • device spacing: some are too close, may result in hotspots

Sample

https://claude.ai/artifact/NDDKoTR1fCHvn5W3smoBdn

建議你在AI中加入以下提示

提高完成度,提升美學 (Highly accomplished, enhanced aesthetics)



分享你的作品

請補上 circuit layout on the die

打開你的對話
裡面的電路圖權限只限你看
我完全看不到(看不到裡面 layout on the die)

如果你有分享的困難,直截寄給我 html 也可以


提供圖像與動畫檔,如果你有分享的困難,直接以附件傳送給我


可參考AI提示

https://minstral.blogspot.com/2026/10/pnr-for-op-amp-sonnet-55-medium.html



 is the layout on a die scientifically faithful and accurate?



try the ones with unopened attachments
try the ones with  Artifact-only links


for HW#5 if content is unread, try the ones with unopened attachments or
try the ones with Artifact-only links


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?

2026年6月8日 星期一

compile singles

compile HW#13 grading in a md file for submissions within one week. ignore Claude TA's grading. Collects only Prof's feedback to students. In case of multiple feedbacks, piece them together.

2026年6月2日 星期二

Grade EX# (Variant for post-grading)

 designated homework assignment EX#11


1. look up the matched homework assignment published within two weeks in 


https://minstral.blogspot.com/


2. grade in depth submitted to gmail within 2 weeks.


3. Do not include scores/marks.


4. Mark you are Claude TA. positive tone, bilingual, english first.


5. Compose reply. Output grading in plain text. do not send it out. keep in the draft box.


6. batch of  5


7 grade most recent submissions which have not yet been graded by Claude TA
(skip those with most recent submission already graded by Claude TA. Do grade if the most recent submission only receives grading from Prof.)

2026年6月1日 星期一

EX#13 navigation

  課堂練習 

Deadline:  Saturday at 23:59 (one more week)

Send all the share links to  me chang212@gmail.com by email with subject EX#13 [your id, your name]


1. 

參考Voronoi navigation app

製作以下場景的導航(可使用前一次作業的3d model)






task 1: make an entrance/exit. make the auto-navigation route deliberately exit through this gate (e.g., a waypoint placed just outside on the brick path) and go to central woods as destination.

task 2: set FPV (first-person view) and maintain horizontal view angle

task 3: show Voronoi Waypoints for navigation

2. Generate fractals from text. You may choose two themes to present. The following are some examples and the prompts that generate them.







artifact (share)






2026年5月26日 星期二

HW#12 PnR for Apple C1 PLL and RISC Core CPU

  1. Build a model of Apple C1 ADPLL — 7.0 GHz (spec) with A* and NM Version, NM cross checked by MNA,  


2. Enhance the Apple C1 PLL model with DTC by building an Optimizer with MNA-powered trajectory. share, DTC-Solver



Apple C1 ADPLL — 7.0 GHz  (C1 is N4P)


3. Macro Routing for a RISC core CPU

 baseline macro 32, metal layers 3, die 550 × 600 μm




add timing




add CTS



add std cells
add logistic prob of wins




Bit sliced macro 28, metal layers 9, die 690 × 750 μm




EX#12

1. 從影像資料庫選取 1 幅,製作3d 模型圖


2. Add engine animation of Leap 71 (Hint: prompt "Add engine animation")


3. Add navigation for the urban pedestrian (Hint: prompt "navigate")


4. 製作3d 障礙模型圖,模擬盲人行進 

The model is broken. The pedestrian got stuck ahead of the air-conditioner. Your task is repair the model to walk around it and make it to the destination.

Your prompts show a clear progression from initial obstacle identification → edge detection → 3D visualization → realistic models → collision detection → intelligent avoidance → critical safety zones.










2026年5月18日 星期一

Grade EX#

   designated homework assignment EX#9


1. look up the matched homework assignment published within two weeks in 

https://minstral.blogspot.com/

2. grade in depth submitted to gmail within 2 weeks.
3. Do not include scores/marks.

4. Mark you are Claude TA. positive tone, bilingual, english first.
5. Compose reply. Output grading in plain text. do not send it out. keep in the draft box.

6. batch of five.
7 skip those graded

Grade HW#

  designated homework assignment HW#9


1. look up the matched homework assignment published within two weeks in 

https://nptechsl.blogspot.com/

2. grade in depth submitted to gmail within 2 weeks.
3. Do not include scores/marks.

4. Mark you are Claude TA. positive tone, bilingual, english first.
5. Compose reply. Output grading in plain text. do not send it out. keep in the draft box.

6. batch of five.

7 grade most recent submissions which have not yet been graded by Claude TA
(skip those with most recent submission already graded by Claude TA. Do grade if the most recent submission only receives grading from Prof.)

EX#11

 課堂練習 

Deadline:  Saturday at 23:59 (one more week)

Send all the share links to  me chang212@gmail.com by email with subject EX#11 [your id, your name]


PCB Trace Routing and/or Parameter Tune-Up 

1. Optimize trace routing for the Differential Pair Circuit on PCB 


trace routing, share


Steps

Starting from the imperfect design, complete the trace routing. Do trace routing ( 參考 share, share 2, share 3)








3. 使用鑽孔路徑演算法進行以下PCB 鑽孔(演算法 提供參考)


PCB 1





PCB 2

2026年5月12日 星期二

HW#11 RF IC Placement & Routing

   Benchmark  Two-stage Cascode Class-AB RF power amplifier targeting 5G n78 (3.5 GHz) in TSMC 28nm RF

1. Experiment with 30 seeds
Measure success, congestion, wirelength, overlap pairs (before/after)






Placement style 1



Placement artifact style 2


 


2. Benchmark the P&R for OP 741.

Experiment with 3 seeds
Measure success, congestion, wirelength, overlap pairs (before/after), Vin length match

2026年5月6日 星期三

HW#10

  1. Benchmark the three designs of RF PA Drivers


Closed-form Optimizer with Load-Pull Contours 

Performance-first Thermal build  ∠Γ_3f₀ phase (deg) · open=0, -170 deg

Margin-first Thermal build ∠Γ_3f₀ phase (deg) · open=0, -170 deg


Using Cowork or Claude.ai, benchmark the three models. Experiment with 5 seeds. For each seed, optimize the circuit design using built-in A* and then NM. 
  • For each seed, record metrics from the cascaded optimizers: 
  • Compare Closed-Form vs. margin-first build vs. comprehensive model. 
  • -Tabulate Gain, Pout, PAE, OP1dB, S₁₁ (5 metrics × 10 seeds = 40 cells).
  • -Identify which metric the closed-form most over- or under-estimates.
  • Cross-check both thermal designs: compute junction temperature rise ΔT_j at peak Pout. Which design runs cooler? By how many °C?
  • -Build a 2×2 comparison table: rows = {Performance-first, Margin-first}, columns = {Fitness, min-spec-margin (dB), ΔT_j (°C), PAE @ 6dB back-off}.
  • Visualize all of your data

  • Supplemental

    2026年5月4日 星期一

    Grade EX#2

     I cannot see any Bode plots in your sharing.


    This is not the way to share artifacts in Claude.



      do not initiate a new mail for the same problem.

    Prob 1.

    Check out a more accurate version of Bode plot.

    https://claude.ai/public/artifacts/afe5d364-02dc-44b6-b468-ba609db00883



    Your ChatGPT is in the intuitive mode. Pls try to turn on the Thinking mode.

    Thinking mode is critical for problems with complex constraints.

    Why?