Peggy Wu's Life Lab | Trying ChatGPT Live with My Kids: What Worked, What Didn't, and Some Advanced Tips

A few days ago, I had dinner with some friends, and one of them shared a Reels video introducing the new ChatGPT Live feature.

As someone who loves trying new tools (especially AI tools 😄), I watched the video and immediately thought, "I have to try this."

The first thing I did after watching it? I grabbed my kids and asked them to be my guinea pigs.

At first, I was simply curious whether talking with ChatGPT would really feel as natural as everyone claimed.

After spending an evening testing it, I realized the most valuable part wasn't actually the conversation itself, it was everything that happened after the conversation.

In this post, I'd like to share my experience, the challenges we ran into, and the workflow that has worked well for us. Hopefully, it will also be helpful if you're looking for a fun way to practice English with your children, or even improve your own workplace English.

Now, here's what I discovered after spending an evening experimenting with it.

It Didn't Go Smoothly at First

Our first conversation lasted less than five minutes before things got awkward.

The biggest problem wasn't that my son was afraid to speak.

It was that ChatGPT sounded too much like a real native speaker.

Since it was their first time talking to an AI, my kids weren't sure what to say and looked a little uncomfortable. On top of that, ChatGPT spoke at a natural pace. Whenever an unfamiliar word came up, they immediately got stuck and couldn't keep up with the conversation.

So the first thing I did was adjust how ChatGPT interacted with them.

Here are the settings that worked best for us:

• Speak slowly.
• Ask only one question at a time.
• Say each question in Chinese first, then in English.
• Wait until they finish answering before asking the next question.
• Correct grammar mistakes immediately.

Once I made those adjustments, the conversation became much more relaxed and enjoyable.

You Don't Need Any Textbooks

I didn't prepare any learning materials.

Instead, we simply talked about things my kids already knew well:

• Badminton
• What they did today
• Their favorite sports
• Competitions
• Muscle soreness or injuries
• Summer vacation

Whenever they didn't know how to say something, I encouraged them to ask ChatGPT directly.

For example, my son wanted to say "ice it" but couldn't remember the English phrase. He simply asked ChatGPT, learned the expression, and then repeated the whole sentence.

That day we also learned words like:

• improve
• sore
• ankle
• ice it
• the difference between hobby and habit

Because the vocabulary came from things they genuinely wanted to express, it was much easier to remember than memorizing random word lists.

The Best Part Happens After the Conversation

After finishing our conversation, I asked ChatGPT to organize everything we had practiced.

For example:

• A complete transcript of the conversation
• New vocabulary
• Common grammar mistakes
• Frequently confused words (such as hobby vs. habit)
• A brand-new practice dialogue based on today's conversation
• A review sheet my kids could use the next day

To me, this is what makes ChatGPT different from most English-speaking apps.

One conversation automatically becomes tomorrow's learning material.

How I Currently Use It with My Kids

This is the prompt I usually give ChatGPT:

• Use simple English.
• Speak slowly.
• Ask one question at a time.
• Say each question in Chinese first, then in English.
• Correct grammar mistakes immediately.
• Summarize everything after the conversation.

This makes my kids feel much less nervous and much more willing to speak.

If your children are still young, I'd also recommend sitting beside them and practicing together.

Interestingly, when I introduced the same method to my older son, who's in high school, he quickly started chatting with ChatGPT on his own. 😄

How I Plan to Use It for Myself

Besides helping my kids, I can already see plenty of opportunities to use ChatGPT Live for work.

For example:

• One-on-one meetings
• Small talk
• Presentations
• AI demos and sharing sessions
• Conversations with overseas colleagues

After each conversation, I can also ask ChatGPT to:

• Review my most common mistakes
• Rewrite my answers in a more natural way
• Create a personalized vocabulary list
• Generate another practice scenario based on today's conversation

That means every practice session builds on the previous one.

I'll probably write another post once I've used it more extensively for workplace English.

Final Thoughts

Before trying ChatGPT Live, I expected it to be a pretty good AI conversation partner.

After actually using it, I think it's much more like a patient English tutor.

The conversation itself is only the beginning.

The real value comes from how it organizes everything you've learned and turns today's conversation into tomorrow's lesson.

For kids, it helps build speaking confidence.

For professionals, it's a great way to improve workplace English.

We'll definitely keep using it at home, and I'd love to hear how you're using ChatGPT Live as well.

💡 PeggyWu's Life Lab Notes

At first, I thought the best part of ChatGPT Live was its voice conversation feature.

After using it for a few days, I realized the real magic is this learning cycle:

Talk → Correct → Summarize → Practice Again

Every conversation becomes the starting point for the next one.

And that's what makes learning feel continuous instead of repetitive.

Peggy 的實驗空間｜陪孩子試用 ChatGPT Live，一些心得與進階玩法

最近和好友聚餐，聊天中好友分享了一支介紹 ChatGPT-Live 新功能的 Reels。

身為一個看到新工具就想實際玩玩看的人（笑），看完介紹後，第一件事，就是抓孩子一起來試。

原本只是想看看語音聊天到底有沒有大家說得那麼自然，沒想到實際玩了一輪後，我覺得最有價值的居然不是聊天，而是聊天結束後的整理能力。

這篇就把這次的實測過程、踩過的坑，以及我目前覺得不錯的使用方式整理下來，希望也能提供給想陪孩子練英文，或是想練職場英文的朋友參考。

Reels（from 哈利說)：https://www.facebook.com/reel/2133540400523945

如果你還沒看過，可以先看這支影片，大概 1 分鐘就知道 ChatGPT Live 在做什麼。

以下分享我實際玩了一個晚上的心得，以及我後來延伸出來的幾個進階玩法。

一開始，其實沒有想像中順利

第一次開始聊天，大概不到五分鐘就卡住了。

主因不是因為孩子不敢開口，而是 ChatGPT 太像真的外國人。

孩子和它不是很熟，會覺得聊天很尷尬不知道聊什麼，我一直看到孩子露出尷尬的表情。另外它講話速度正常，遇到不知道的單字，小朋友就卡住，出現問號，所以很快就跟不上。

我做的第一件事情，就是先調整聊天方式。

目前覺得最適合孩子的設定是：

• 請它講慢一點（Please speak slowly.）
• 一次只問一個問題（Please ask one question at a time.）
• 每一句先中文，再英文
• 等孩子回答完，再繼續下一題
• 有文法錯誤就立刻修正

做了這些調整完之後，整個對話就順多了。

（下圖是其中的一個調整）

不用準備教材，聊孩子每天熟悉的事情

沒有準備什麼英文教材，從我們孩子每天最熟悉的內容，例如：

• 羽毛球
• 今天做了什麼
• 喜歡什麼運動
• 比賽
• 身體哪裡痠痛
• 暑假生活

另外我也鼓勵小朋友不會的單字直接問，例如想說「冰敷」但突然忘記，就直接問英文怎麼說，問完再整句講一次。

例如今天就學到：

• improve（進步）
• sore（痠痛）
• ankle（腳踝）
• ice it（冰敷）
• hobby / habit 的差別

因為都是「真的想表達」，所以印象比背單字深很多。

聊天結束之後的 summary

聊天結束後，我請 ChatGPT 幫我整理今天的內容。

例如：

• 今天完整的英文對話
• 今天的新單字
• 今天最常犯的文法錯誤
• 容易搞混的單字（例如 hobby / habit）
• 再重新產生一篇新的練習對話
• 幫孩子整理一份可以直接複習的教材

這一步，我覺得是 ChatGPT 和一般英文口說 App 最大的差異，一次聊天，可以變成下一次的教材。

陪孩子練習，我目前會這樣使用

固定請 ChatGPT： 

• 用簡單英文 
• 講慢一點
• 一次只問一個問題
• 每一句先中文，再英文
• 有錯立刻修正
• 對話結束後整理今天的內容

孩子比較不會有壓力，也比較願意開口。另外孩子還小的，還是會需要家長陪伴著。同樣的學習方法我分享給高一的哥哥，他就自己聊開了 （笑）。

如果是我自己，我會怎麼用？

陪孩子之外，其實很多工作上也很有練習的空間。

例如：

• One-on-One
• Small Talk
• Presentation
• AI 分享
• 和國外同事聊天

聊天結束後，再請 ChatGPT：

• 整理今天最常犯的錯誤
• 改成更自然的說法
• 整理新的單字
• 根據今天內容，再設計下一次的練習情境

等於每一次聊天，都可以持續累積。這部分我之後如果有更深刻的不同體驗再寫一篇分享。 

我目前最大的心得

原本我預期 ChatGPT-Live 是一個蠻不錯的英文陪聊工具。

實際玩了一輪之後，我覺得它比較像一位很有耐心的英文老師，聊天只是一個開始。

真正讓我會想持續用下去的原因，是它可以把今天的對話整理成下一次的教材。

對孩子來說，可以累積口說能力；對上班族來說，也可以累積職場英文。

目前我們家應該會繼續用這個方式練習一陣子，也歡迎大家一起交流，更多有趣的用法。

💡 Peggy 的實驗筆記

我原本以為 ChatGPT Live 最厲害的是「語音聊天」，實際玩過幾天後，我覺得真正的價值是：

聊天 → 更正 → 整理 → 再練一次。

這讓每一次聊天，都變成下一次學習的起點。

喜歡此篇文章的朋友，歡迎轉貼與留言。轉貼時請保持原內容與註明原文標題、連結以及作者即可，謝謝您。

Peggy Wu's Life Lab | One Idea, A Group of Passionate Teammates, and an AI Tech Talk

 

Thanks to John, Jersey and Mandy for helping make the first AI Tech Talk in our Taipei office a reality!

We had more than 70 colleagues join online and over 40 attend in person (with some overlap between the two), which was far beyond what I originally expected.

The idea behind it was actually quite simple.

Whenever I chatted with friends and colleagues from different teams, I noticed that everyone had developed their own ways of using AI. People had discovered useful workflows, built their own habits, learned hard lessons, and accumulated plenty of practical experience along the way.

What felt a little unfortunate was that there weren't many opportunities for those experiences to be shared across teams.

Sometimes the challenge you're facing today is one that someone else has already solved. Sometimes a mistake someone else has already made can save you from making the same one yourself.

One comment I kept hearing recently also stuck with me:

"AI is probably the person I talk to the most every day."

It always made me smile, but it also reminded me of something important.

As AI becomes a bigger part of our daily work, opportunities for people to learn from one another face-to-face may actually become even more valuable.

Another motivation was to create a more relaxed and accessible environment where people could exchange ideas and experiences more freely. Over time, I hope this can grow into an internal AI community where colleagues can connect, share, and learn from each other.

To be honest, I hesitated before deciding to organize the Tech Talk and start building the community.

Besides being busy with work, I kept wondering:

"If AI agents are getting smarter every day, do people still need something like this? Can't everyone just ask AI directly?"

When I shared that thought with John, he immediately encouraged the idea. Jersey was equally supportive.

At that point, it felt like there was only one reasonable answer:

Let's do it.

I'm incredibly grateful to both of them for their encouragement and support. I'd also like to thank our amazing Office Manager for helping everything come together so smoothly.

With teammates like these, it became hard to find a reason not to move forward.

A special thank-you also goes to our two speakers who volunteered to kick off the first session.

Despite their busy schedules, they took the time to organize their experiences, prepare their materials, and join us in person to share what they've learned. That generosity is what makes a community possible.

I should also admit that I had a small personal motivation.

Of course I wanted to learn from experts within my own team, but I also wanted an opportunity to meet talented people from other parts of the company, understand how they think, and learn how they are using AI to improve the way they work.

Finally, thank you to everyone who attended, joined online, and asked thoughtful questions.

Seeing people willing to share, exchange ideas, and help one another is exactly what I hoped for when this started.

And hopefully, this is only the beginning.

Peggy的實驗空間｜一個想法、一群熱心的夥伴，和一場 AI Tech Talk

感謝 John , Jersey and Mandy一起辦成了台北 Office 第一次的 AI Tech Talk！

這次線上有超過 70 位同事參與，現場也來了超過 40 位夥伴（可能有部分重複參與），比原本預期熱烈許多。

其實當初起心動念很單純。

平常和不同部門的朋友聊天時，常常發現大家都已經發展出自己的一套 AI 使用方式與工作流程，也踩過不少坑、累積了很多心得。但因為跨部門交流的機會有限，這些寶貴經驗不一定有機會被分享出來。

有時候自己正在遇到的問題，可能早就有人解決過；而別人踩過的坑，也可能正是自己即將踩進去的地方。

更有趣的是，這陣子不只一次聽到同事開玩笑說：「現在每天講最多話的對象就是 AI。」也讓我更覺得，在 AI 時代裡，人與人面對面的交流反而變得更珍貴。

另外一個想法，是希望能有一個更輕鬆、更自在的中文交流環境，慢慢形成公司內部的 AI Community，讓大家更容易分享經驗、互相學習。

老實說，在決定要不要辦這個 Tech Talk 以及建立 AI Community 之前，我內心其實有點掙扎。除了工作本來就很忙之外，也曾想過：現在 Agent 越來越強，大家是不是自己問 AI 就好了？

後來和 John 聊起這個想法時，他非常支持；Jersey 也立刻表示贊同。既然有這麼多人的支持，那就辦吧！

非常感謝兩位一路鼓勵與幫忙，也感謝美麗又強大的 Office Manager Mandy 全力支援。有這樣的隊友，好像真的找不到不辦的理由。

也特別感謝這次打頭陣分享的兩位優秀同事。在繁忙的工作節奏中，願意花時間整理自己的實戰經驗，甚至親自到現場和大家交流，真的非常難得。

當然，我自己也有一點私心。

除了能向部門內的高手學習之外，也希望藉著這樣的活動認識更多來自不同團隊的強者，向他們請教、學習，看看別人是如何思考問題、如何運用 AI 提升工作效率。

最後，也想謝謝所有到場參與、線上收看，以及踴躍提問的同事們。

看到大家願意分享、願意交流、願意彼此幫助，正是我最期待看見的事情。

期待這只是開始。

Peggy Wu's Life Lab | Claude Code Didn't Change My Coding. It Changed How I Work.

 

Lately, whenever I get together with friends, our conversations somehow end up revolving around AI tools such as Claude Code, Codex, ChatGPT, and Copilot.

When I stop and think about it, Claude Code has quietly become an indispensable part of my daily work over the past few months. One of my teammates recently joked that the person he talks to most every day is no longer his family or coworkers. It's Claude Code. 😄

Like many people, I started by experimenting. Over time, I gradually found a workflow that fits the way I work. It has saved me a significant amount of time and made many repetitive or tedious tasks much easier.

But looking back, the biggest benefit wasn't learning a new tool. The more interesting change was how it gradually changed some of my work habits.

Here are the three changes I've noticed the most.

1. I've Become More Protective of My Focus

When I first started using Claude Code, I loved the feeling of doing multiple things at once. One agent was analyzing a problem, another was gathering information, and a third was writing code. At the same time, I was replying to Slack messages, reviewing Jira tickets, and discussing pull requests with Copilot or Claude.

For a while, it felt incredibly productive.

There was even a period when I had several Claude Code windows running simultaneously, each handling different tasks in the background. I've always been fairly confident in my ability to multitask, so watching everything move forward at the same time felt rewarding. My output increased, and I genuinely felt like I was operating at a higher level than before.

The problem was that something else increased as well: my fatigue.

After a few weeks, I started noticing that I felt mentally drained at the end of the day. Sometimes the feeling even carried over into the next morning. There were nights when I went to bed knowing I had accomplished a lot, yet my brain felt completely exhausted.

Eventually, I realized what was happening.

Claude Code was reducing the effort required to execute tasks, but it wasn't reducing the effort required to manage attention. Every time I switched contexts, jumped between conversations, or tried to remember where I had left off, there was still a cognitive cost.

Once I recognized that, I started making deliberate adjustments. I stopped checking every running agent every few minutes. I became more comfortable focusing on one important task at a time. Instead of letting multiple windows constantly compete for my attention, I tried to be more intentional about where my focus went.

After a few weeks, I noticed a meaningful difference. The quality of my work became more consistent, and my energy levels felt much more sustainable.

The irony is that Claude Code gave me more ability to multitask. What it ultimately taught me was the value of focus.

2. I Spend More Time Thinking Before I Start

If you give me a problem, my instinct is usually to jump in and start solving it immediately.

That tendency became even stronger when I first started using Claude Code. Everything felt fast. Ideas could be tested instantly. If something didn't work, I could simply change direction and try again.

To be honest, it felt a bit like getting a new toy as a child. You don't read the instructions. You just start playing and figure things out along the way.

The problem is that many of the apparent time savings weren't actually savings. I was simply postponing the thinking.

If I hadn't fully understood the requirements, clarified the edge cases, or defined what success looked like, I would eventually spend the time anyway through revisions and rework.

One experience stands out clearly in my memory. I enthusiastically started implementing a solution, only to realize halfway through that I had misunderstood a key requirement. Most of the work I had already completed needed to be redone. It was frustrating, but it taught me an important lesson.

The problem wasn't Claude Code.

I simply hadn't thought things through.

These days, whenever I'm working on something more complex, I take a different approach. Before I start building anything, I spend some time organizing my thoughts. If there are known requirements, I try to document them clearly and answer a few simple questions:

• What problem are we actually trying to solve?

• What approach, logic, and steps make the most sense?

• What does success look like?

It's essentially a lightweight design document. Nothing formal or complicated. Just enough structure to make sure the direction is clear.

Then I ask Claude to review the plan. I encourage it to challenge assumptions, point out risks, and ask questions. Quite often, those questions reveal gaps in my own thinking that I hadn't noticed.

Only after the plan feels solid do I move into execution.

The biggest benefit isn't speed. It's avoiding unnecessary rework. More importantly, it has reminded me that productivity often depends less on execution and more on the quality of thinking that happens before execution begins.

3. I Spend More Time Working on Real Bottlenecks

If you asked me about the biggest benefit I've gained from the past few months, my answer wouldn't be automation.

It would be perspective.

For the first time in a long while, I feel like I have more room to think beyond the immediate task in front of me.

When work gets busy, it's easy to focus entirely on execution. Is the feature finished? Is the bug fixed? Has testing been completed? Before long, every day becomes a race to get through the next item on the to-do list.

But the longer I've worked as a manager, the more I've realized that the biggest obstacles to team productivity rarely live inside the code itself.

More often, they live inside processes, communication, and organizational structure.

Recently, during one-on-one meetings, I've started asking a simple question:

What's the biggest thing slowing you down right now?

The answers vary. Sometimes it's technical. Sometimes it's procedural. Sometimes it's a cross-functional issue. Sometimes it's something surprisingly simple.

I remember one discussion where I initially assumed we were dealing with a difficult technical challenge. After digging deeper, we discovered that the real issue was unclear ownership between teams. The problem had been slowing progress for weeks, and no technical solution was going to fix it.

Many of the most important bottlenecks require communication, alignment, judgment, and prioritization. Those are still very human challenges, and they remain an important part of leadership.

The time Claude Code saves me doesn't necessarily lead to more coding. Instead, it gives me more opportunities to focus on things I've always known were important but never seemed urgent enough to prioritize.

Final Thoughts

Looking back, what stands out most isn't how much faster things have become, although they certainly have. Research is faster. Writing is faster. Coding is faster. Testing ideas is faster.

But as execution becomes easier, other constraints become more visible.

Focus.

Thinking quality.

Communication.

Alignment.

These things haven't become less important. If anything, they've become more important.

When everyone has access to powerful tools, the difference is no longer just who can move faster. It's who understands what matters, who can identify the right problem, and who can focus their energy where it creates the most value.

For me, that's been the biggest lesson of the past few months. Claude Code didn't simply change how I write code, it changed how I think about work. And it left me with a question I'm still exploring:

As more routine work becomes easier, where is my time most valuable?

I don't have a perfect answer yet.

But I suspect that question matters far more than learning the next tool.