Created a three-tab interactive webpage on Simple Machines using Poe

 AI TOOL USED: 

- Poe's Canvas Creator

PROMPT

Create an app for upper primary students to learn about Simple Machines. Refer to the following picture for the format.

Learning Objectives:

• I can tell the names of the parts of a simple machine.
• I can label the picture of a simple machine.

There should be 3 tabs across the page below 'Learning objectives'.

• The first tab, titled 'Simple Machine', opens a picture with the parts of a simple machine labelled.
• The second tab, titled 'Quiz', opens up a few multiple choice questions about simple machines.
• The third tab, titled 'Simple Machine Labelling', opens up a diagram labelling task for students to label the parts of a simple machine.

OUTPUT:

https://poe.com/Simple-Machines

(Users need to sign in with their Poe account.)

Generating an infographic from a chat output: Direct in Gemini from an output vs Copy Output and generate in Image

 What I did: 

1. I asked Gemini chatbot: What is the relationship between Metacognition and Language Awareness? 

2.  I obtained the output from Gemini. 

3. While staying in the chatbot mode, I immediately asked Gemini to create an infographic based on the output. 

4. Below is what I obtained? 

I then tried another route. 

- I copied the earlier output from Gemini. 

- I went to Gemini Image, pastedd in the output, and asked for an infographic. 

- Below is the image output. 

==========================================

OBSERVATION

The first infographic looks better. It's easier to understand. The second one is a bit confusing, and too texty. 

TAKEAWAY

- Follow the first approach. 

Created a PPT slidedeck using built-in Copilot: Good Results

 My Workflow: 

1. I prepared a point-form summary of What is Metacognition in WORD. 

2. I opened PPT, and chose 'Create with Copilot.' A side pane appeared on the right.

3. I uploaded the above WORD, asked Copilot to turn it into a PPT, sticking to the content of the WORD WITHOUT adding in more content ideas. 

4. After answering a couple of parameter questions (eg, style), it started to generate the slidedeck. 

THE OUTPUT: 

TAKEAWAYS

1. Output better than other apps like Gamma and SlideAI. It doesn't add in additional content ideas. 

2. The points are presented in graphic forms in many of the slides. 

3. The initial output lends itself to revision. (For example, I asked it to enlarge the font size a little.)

4. The biggest problem: The long time it takes. 

Tried out PPT slides.ai add-on: Still not meeting my needs

 Tried out the add-on. 

1. There are 4 ways to start. The script method, which makes use of only the script uploaded, is a paid feature. 

2. For the free plan, you can start with a topic. You can also paste in a text, but it may generate new contents. 

3. I used the result of a Gemini chat on SRL; pasted it into the prompt box, which has word limit. 

OUTPUT

- very texty

- minimal visuals included

- suitable for reading, but not for presenting a lecture from. 

==========================================================

The built-in Copilot function is free. It can stick to your input text. It generates some visuals, which are usually graphics, that relate to the content of the slides. The biggest minus is its very slow speed. 

Using Copilot in PPT to generate a slidedeck from a bulleted-list outline

 我備課時如果要製作Powerpoint, 一定不會立即開Powerpoint app然後逐張slide打入內容，因為這樣做一來慢，二來打了六，七張slide後很易迷失大方向。我會先在WORD  以point form 打出內容，然後以outline 格式儲存，然後import into Powerpoint，便會convert成一個slidedeck, 如果要好看，當然仍要在一些slide design editing。

但今天有了M365 Copilot, 打開Powerpoint 後，開啟Copilot, paste in 自己的point-form outline, Copilot便立刻生成一個有設計的slidedeck, 乾手净腳，惟一缺點是慢。

其他類似的AI app 如Gamma 和Beautiful.ai, 一來不是免費，二來會加人純裝飾沒有作用的image。

Creating an infographic from a summary generated by Gemini Chat: Gemini Chat vs Gemini Image

 My workflow:

1. In Gemini:

- prompt: 

    Provide a summary on the relationship between metacognition, self-regulated learning, and learner autonomy in about 100 words. 

- Still within Gemini Chat, I asked it to turn the summary into an infographic. 

OUTPUT: 

========================

2. In Gemini Image

- I copied the earlier summary, and went to Gemini Image.

- I pasted in the summary, and asked for an infographic: 

Metacognition, self-regulated learning (SRL), and learner autonomy form a deeply interconnected hierarchy in language education.

Metacognition is the cognitive foundation—the "thinking about thinking" that allows learners to plan, monitor, and evaluate their own learning processes.

SRL operationalizes this awareness; it is the active behavioral translation of metacognition into specific strategies, goal-setting, and emotional management during a learning task.

Learner Autonomy is the ultimate pedagogical goal. It represents the broader psychological capacity, willingness, and freedom of the learner to take full control of their own learning journey.

- OUTPUT: 

+++++++++++++++++++++++++++++++++++++++++++++++++++++

TAKEAWAY: 

- Difficult to say which one is bettter; the two outputs present the summary in different ways. 

Created a Typing Challenge game directly with Gemini Canvas and with Canva Code for Me

 I then tried directly asking Gemini Canvas to create the Typing Challenge, this time involving Colour Words. Gemini Canvas was able to do that from a prompt:

Prompt: create an interactive typing challenge game for upper secondary ESL students. The words to type are colour words. 

Output: https://share.gemini.google/7pEPF7CJpDl2

- The output is more complicated than I expected.

- When I tried, it confined itself to a small range of words. 

- Hence, the output needs iteration. But the takeaway is that instead of cloning and revising somebody's typing game, I can also create one directly using a simple prompt. 

==================================

Then I used the same prompt in Canva Code for Me:

The OUTPUT: 

- The page design is very simple.

- But the content is better than that produced by Gemini Canvas. 

TAKEAWAY:

- Canva Code for Me is not bad for creating interactive games. I may just need to do some simple iterations. 

Created an interactive typing challenge from Ha Sir's example bypassing the Code Block step

 Then I tried a more direct workflow that didn't require getting the Code Block first: 

1. I went to Gemini Canvas, and entered the following prompt: 

please revise the following typing challenge, changing the words to type to words which are grammar items:

https://gemini.google.com/share/1b28010945f0?skid=0d2d966a-31cd-48be-8718-ffe2c23d94ea (Ha Sir's original Challenge)

2. Gemini Canvas returned the following: 

https://share.gemini.google/JyR9c5k74naR

...which is actually quite different from Ha Sir's in design. I think Gemini Canvas was simply referring to the idea of Typing Challenge, instead of cloning and modifying Ha Sir's game. 

Cloned and Modified Ha Sir's Typing Challenge App

 1. Ha Sir's original typing challenge (involving IT terms): https://share.gemini.google/QRTbRKkKdkIo

2. I copied his link, went to Gemini, and asked it to create a similar typing game, but involving grammar terms. 

3. Gemini then gave me the Code Block. 

4. I asked Gemini how to turn the Code Block  into a standalone webpage which can be shared with others. Gemini suggested a couple of options, but they were technically too complicated for me. 

5. I copied the Code Block that Gemini had give me already. 

6. I went to Canva's Code for me, and paste in the Code Block. (I didn't write further prompts; just pasted in the Code Block.)

7. Canva Code for Me succeeded in creating a standalone interactive game: 

https://bit.ly/paulsze-grammar-terms-typing-challenge

The capability of today's AI chatbots

 AI chatbots 初初面世時，答問題時只能依賴training data, 於是問題如果涉及最新的景況，它便會說抱歉，不能幫忙。於是我初期只會問一些和人類知識有關的問題。

但今天已是另一個世界，由於AI chatbots 可以搜羅互聯網，於是最新最獨特的問題，都難不到它，例如我最近問Gemini (1) 這個暑假中大有哪些canteen 照常開放？⑵那個You can you up, No can no BB 的告示牌在哪裡可以買得到？Gemini 一樣不用10秒鐘便答得到。

所以到了今天，無論問題有多獨特怪誕，只要你夠膽問AI，都有機會得到答案！

AI capability: A blessing, or a curse in disguise?

 昨天談到AI帶來的方便，例如它為我找到的 一個網上的interactive worksheet 提供answer key，省卻我自己做一次的時間，但同時亦令我再次想到幾個月來一直思考的問題：AI帶來方便，但會否亦使我們逐漸失去一些重要的經驗和能力？例如新一代的教師，會否因而缺乏一個對我來說是非常重要的專業能力：How to design an English lesson from scratch？

Tried out Wordwall's AI functionality to create an interactive game

 WHAT I DID:

1. Choose a game templete. 

2. Uploaded my original worksheet (WORD file) which contained the Answer Key

3. Wrote the prompt: 

please create a 10-question quiz using the content of the uploaded word file. All 10 questions are multiple choice questions. Students look at each given sentence, which contains an underlined word or phrase, and decide which type of reference the underlined word/phrase is. 

For each question, the 3 choices are: 

- anaphoric (A)

- cataphoric (C)

- exophoric (E)

In the attached file, for each of the 10 sentences, the correct answer is given at the end of the sentence (i.e., A, or C, or E). 

4. GENERATE

=======================================

OUTPUT: 

- Usable. Note, though, that the originally formatting in the WORD file, such as highlighting, italics, will not show in the generated task. 

https://wordwall.net/resource/115987359

Generated the quiz text from an online quiz and re-created the quiz in Wayground

 I had the following online quiz on Theme Rheme analysis, but the webpage does not show the Answer Key unless I actually try answering the quiz. Furthermore, I wanted to re-create the quiz in Wayground.  

https://eltconcourse.com/training/inservice/discourse/theme_rhemehp.htm

MY WORKAROUND

1. I went to Gemini, pasted in the link, and asked it to give me the (a) quiz text, and (b) the Answer Key. Gemini succeeded in doing that. 

2. I copied the output into the WORD document, went to Wayground, and started by uploading the WORD document. 

3. I proceeded from there. 

4. Wayground succeeded in turning the content of the WORD file into a quiz: 

https://wayground.com/activity/admin/quiz/6a4d0077dfa5238ccd71767e?aiQuizGen=true&autoSnip=true&aiQuizPublished=true

The best approach: Create the quiz using Gemini's output and use WG's AI functionality

 The previous post compared Gemini and Wayground in terms of generating a quiz from a uploaded PPT. 

I have tried the following workaround which capitalises on the merits of the 2 tools: 

1. Create the Quiz in Gemini. 

2. Copy the questions into a WORD document. 

3. Open Wayground. Start with Upload own content:

4. WG recognises that the content is a quiz, and asks me whether I want to go ahead with a quiz. I said Yes. 

5. There are 2 options:

a. Stick to the questions in the uploaded file; 

b. Generate new questions.

6. CHOOSE OPTION A. 

7. RESULT: WG replicates the uploaded quiz content. 

Created an MCQ quiz from an uploaded lecture PPT: Gemini vs Wayground

 PPT used: PEDU6112 S1: Introduction to Language Awareness

Prompt: Create a 7-item MCQ quiz based on the uploaded PPT

================================================

GEMINI OUTPUT: 

https://share.gemini.google/EJsvQENuDcpZ

- Does not confine itself to the content of the PPT; 

- some Application questions

- level of difficulty: slightly above average

- Output can be in the form of an interactive page. 

- output has to be imported into an AI app like Wayground to track students' performances

WAYGROUND OUTPUT

- In a way, WG is similar to  Gemini in that: 

- it does not follow the content of the PPT slavishly; 

- Gemini's output is more academic and of higher quality

- WG of course has quizzes integrated with the LMS. 

Finally found the time to complete MagicSchool Level 2 certification.

 Finally found the time to complete MagicSchool Level 2 certification.