Name: How to boost your AI skills 🚀 | BBC Ideas
Uploaded: 2026-03-05T17:34:01.000Z
Duration: 4 min 44 s
Description: Thousands of YouTube videos with English-Chinese subtitles! Now you can learn to understand native speakers, expand your vocabulary, and improve your pronunciation...

Adverbs of manner

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

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

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

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

how to pick the right chatbot for your needs.

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

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.

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.

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

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

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

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.

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

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

This demonstrates how the AI understands and connects concepts.

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.

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.

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.

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

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.

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

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

You just steered it to where the angry words live.

Sycophancy can sometimes be a problem when using chatbots.

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

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.

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

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

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.

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.

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

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.

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

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.

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

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.

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.

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

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

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

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.