Name: 如何讓你的AI技能Level Up 🚀 | BBC Ideas (How to boost your AI skills 🚀 | BBC Ideas)
Uploaded: 2026-03-05T17:37:53.000Z
Duration: 4 min 44 s

情態副詞

So you've probably already started using AI chatbots, maybe to create a meal plan or write a difficult email.

所以你可能已經開始使用 AI chatbots 了，也許是為了製作飲食計畫或是寫一封難搞的信。

If you haven't, check out our handy intro guides@BBC.co.uk ideas or ou connect.

如果還沒有，可以看看我們在 BBC.co.uk 上的實用入門指南，裡面有很多點子，或是跟我們聯繫。

But you're not sure you're getting the best out of it, and

但你可能不太確定自己是不是把它的功能發揮到最大，而且

那要怎麼讓你的使用技巧更上一層樓呢？

This short guide will cover how to write better prompts, how to avoid something called AI sycophancy, and

這份簡短的指南會教你如何寫出更好的 prompt，如何避免所謂的 AI sy，還有

how to pick the right chatbot for your needs.

如何挑選適合你需求的 chatbot。

First, you need to appreciate that AI is a machine, a mathematical model, not a thinking being.

首先，你需要明白 AI is a machine，是一個數學模型，不是一個有思想的生物。

When you're giving it instructions or prompts, you're guiding it to give you answers, not asking a magician to conjure up a miracle.

當你給它指令或 prompt 時，你是在引導它給你答案，而不是在請魔術師變出奇蹟。

It can help to think of your chatbot as a small spaceship, which follows your instructions to find the answers from the vast galaxy of interconnected information that's out there.

你可以把你的 chatbot 想像成一艘小太空梭，它會遵照你的訓示，從浩瀚的 AI information galaxy 中尋找答案。

Say you're looking for advice as to what type of dog your family should get.

假設你想知道你的家庭應該養哪種狗。

If you type the question into Google, you'll get results from dog food companies, charities, even banks, and

如果你把這個問題輸入 Google，你會得到來自寵物食品公司、慈善機構，甚至是銀行的結果，而且

some will have paid Google to showcase their results when that question is typed in.

有些公司付錢給 Google，讓他們在輸入這個問題時，能優先顯示他們的結果。

If you put the same question into an AI chatbot, you'll get a long list of different dogs unlikely to be specific to your needs.

如果你把同樣的問題輸入 AI chatbots，你會得到一份長長的狗狗清單，但不太可能符合你的需求。

In fact, it doesn't even know what a dog is.

事實上，它甚至不知道什麼是狗。

In the AI information galaxy, dog is next to puppy bone and walk.

在 AI information galaxy 中，"狗"旁邊是 "小狗骨頭" 和 "散步"。

This demonstrates how the AI understands and connects concepts.

這展示了 AI 是如何理解和連結概念的。

So if you make the connections for it in other words, give it the right context, it's much more likely to produce a useful response.

所以，換句話說，如果你幫它做好連結，給它正確的脈絡，它就更有可能產生有用的回應。

For example, you might try Help me decide which dog would make a good pet for my busy family with three teenage children, two cats and a small garden.

舉個例子，你可以試著問：「幫我決定哪種狗狗適合我這個有三個青少年小孩、兩隻貓和一個小花園的忙碌家庭當寵物。」

Using reliable sources based in the uk, essentially, you're helping it narrow down the vast array of information it can access and navigate to a much more specific bit of the information.

利用英國的可靠來源，基本上，你是在幫助它縮小可存取的龐大資訊範圍，並導向資訊中更具體的一塊。

Another tip to get better results from your interactions with AI is to think about your tone when writing your prompts.

另一個讓您與 AI 互動獲得更好結果的技巧是，思考您在撰寫提示時的語氣。

If you're polite and friendly, you're likely to get polite and friendly responses back because you've steered the spaceship to the friendly word section of the galaxy.

如果你有禮貌又友善，你很可能會得到有禮貌又友善的回應，因為你已經把太空梭導向了星系中友善的詞彙區塊。

If you type an angry prompt, you steer the spaceship into the angry sector of the galaxy.

如果你輸入一個生氣的提示，你就是把太空梭導向了生氣的區域。

The AI isn't becoming angry, it doesn't really have a personality.

AI 並沒有生氣，它其實沒有個性。

You just steered it to where the angry words live.

你只是把它導向了充滿生氣詞彙的地方。

Sycophancy can sometimes be a problem when using chatbots.

使用 AI chatbots 時，AI sy 有時會是個問題。

That's the AI telling you what it thinks you want to hear.

那就是 AI 告訴你它認為你想聽什麼。

This could be awkward at work if you're trying to improve a business process or come up with a new idea and it's constantly telling you that your ideas are brilliant.

如果這在工作場合發生，可能會有點尷尬，尤其當你正想改善商業流程或提出新點子時，它卻一直說你的想法很棒。

One tip to counteract that is to specifically ask the chatbot for different perspectives.

有個方法可以對抗這種情況，就是明確要求 chatbot 提供不同的觀點。

Prompt it with play Devil's Advocate or or are there counter arguments to moving to a four day week?

你可以下指令請它扮演魔鬼代言人，或是問「有沒有反對實施四天工作週的論點？」

Asking the chatbot to explain its reasoning and include sources can also be useful so you can see the journey it's been on and how it's reached its conclusions.

要求 chatbot 解釋它的推理過程並附上來源，也會很有幫助，這樣你就能瞭解它是如何得出結論的。

Hallucinations AI is giving convincing but wrong answers because they've wrongly interpreted something in a bit of the information galaxy they're searching in.

AI 的幻覺是它給出聽起來有道理但錯誤的答案，因為它在搜尋的 AI information galaxy 中誤解了某些資訊。

They're getting rarer, but they're absolutely still out there.

雖然這種情況越來越少見，但還是確實存在。

So it's important to fact check AI responses by comparing them to reliable sources you trust and think carefully about which chatbot you're using.

所以，透過比對你信任的可靠來源來事實查核 AI 的回應，並仔細思考你正在使用哪一款 chatbot，這點很重要。

Different models have been trained on different material and may have different biases.

不同的模型經過不同資料的訓練，可能會有不同的偏見。

They also have different tones, so a model like Grok, the AI developed by X, is likely to give you a more sarcastic answer than one developed for a corporate client by a firm like Microsoft or Google.

它們的語氣也不同，所以像 X 開發的 Grok 這款 AI，可能比微軟或 Google 等公司為企業客戶開發的模型，給出更諷刺的答案。

Be aware of the impact of so called guardrails on results.

要注意所謂的 guardrails 對結果的影響。

For example, some AIs are designed with safety in mind which could be helpful like warning you not to self harm or download illegal content.

舉例來說，有些 AI 的設計考量到安全性，這很有幫助，像是提醒你不要傷害自己或下載非法內容。

But guardrails could be downright annoying if, for example, you're trying to research the 1989 Tiananmen Square protests using a Chinese chatbot which has censorship built in.

但如果，你試圖用內建審查機制的中文 chatbot 來研究 1989 年天安門事件，那麼這些 guardrails 就可能非常惱人。

In short, if you're going to get the best out of AI, use it carefully.

總之，如果你想從 AI 獲得最好的成果，就要小心使用。

Think about what you're asking it to do and how it can.

仔細想想你請它做什麼，以及它能做到什麼。

Great as a tool for brainstorming and support in making decisions, but

它很適合當作腦力激盪和輔助決策的工具，但

it's not a replacement for critical thinking.

If you understand its mechanics, limitations and biases, you'll treat it as a useful tool, not a magician.

如果你瞭解它的機制、限制和偏見，你就會把它當成一個有用的工具，而不是魔法師。