Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Paul Couvert

@itsPaulAi

Jan 19, 2024 • 6 tweets • 3 min read • Read on X

Scrolly

Copilot has a new feature that I love.

It's called Notebook and it's completely free.

This allows you to test your prompts for GPT-4.

Here's exactly what it's used for and how to use it:

1. Access Notebook

- Go to copilot .microsoft .com

- Select the mode you want (I recommend "Creative")

- In the top menu, click on "Notebook".

Important notes:

1. The mode you select seems to influence the mode used by Notebook. Select Creative or Precise for GPT-4.

2. You have a limit of 18,000 characters, unlike chat, which has a limit of 4,000.

2. Write your prompt

- Test your 1st prompt on the left.

- Send it to see the result with GPT-4 on the right.

Notebook makes it easy to test your prompts without having to create a new conversation each time!

3. Fine-tune your prompt

- Make changes to your prompt

- And send the new version for comparison

This is a huge time-saver, rather than starting from scratch every time in a chat.

Bonus: export

As with Copilot's chat function, you can export the result.

Click on the arrow to download in Word, PDF or Text format.

https://twitter.com/itsPaulAi/status/1748388577418047572

Having an interface to test and fine-tune your prompts is great:

You don't have to waste time creating a new conversation when you want to create the perfect prompt!

If you found this useful, please like and share the first post:

https://twitter.com/itsPaulAi/status/1748388577418047572

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @itsPaulAi

Paul Couvert

@itsPaulAi

Sep 11

Google has published AI Edge Gallery on the store 🔥

So you can do everything 100% locally on your phone:

- Upload images and ask questions
- Transcribe/translate audio files
- Summarize, rewrite, code
- Engage in multi-turn conversations

Steps to use it below (open source):

1. Download Google AI Edge Gallery

- Go to the Play Store
- Search for “Google Al Edge Gallery”
- Download the app shown in the screenshot below

2. Select a mode

- Click on the mode you want to use.
- Select the Gemma model.

Note: the larger it is, the better it'll perform, but the slower it'll be.

If you've a less powerful phone, choose the smallest model.

Read 5 tweets

Paul Couvert

@itsPaulAi

Aug 31

You can combine Nano Banana with a video model to generate impressive results!

It literally takes just a few minutes.

Steps of the workflow below

1. Nano Banana

Import your original image into Gemini App or AI Studio.

Then simply ask it to transform the room (or other object) into an isometric view.

Repeat the process for your second image.

https://x.com/itsPaulAi/status/1959829275852312772

2. Video

You're almost done:

- Import your images into an image-to-video template.

- Use the first one as the start frame and the last one as the end frame

I personally use Kling (I've created a quick tutorial right here) ↓

https://x.com/itsPaulAi/status/1959829275852312772

Read 4 tweets

Paul Couvert

@itsPaulAi

Aug 25

Ok AI video gen is evolving really fast

You can now set the EXACT start and end frames before generating.

This means you can literally control your entire video with just 2 images and let AI fill the video in between.

Steps to do it using Kling 2.1

You just need 2 images:

- First frame of your scene (where the video begins)
- Last frame (where it ends)

In Kling 2.1, select "AI Video Generator" then "Image to video."

1. Upload your start image then your end image
2. Type a prompt if you wish
3. Click "Generate" and voilà!

Here’s another quick example:

You can easily control the whole scene and the transition by choosing the right start and end frames.

Read 4 tweets

Paul Couvert

@itsPaulAi

Aug 15

Google has released a new open source model...

That runs on just 0.5 GB of RAM. Yes.

You can fine-tune it for free to make it better than the giant models at your tasks.

Quick steps to fine-tune Gemma 3 270M below

We're going to use the free Google Colab from Unsloth.

Steps:

- You've a general-purpose base model
- You want to teach it to work like you (eg. newsletter writing)
- Show it examples of past work (=training data)
- It'll learn your style, tone, formatting...

Link at the end

1. Setup and installation

This part installs Unsloth and all the other tools needed to fine-tune the model.

You don't need to change anything here; just run it.

Read 12 tweets

Paul Couvert

@itsPaulAi

Aug 13

Gemini released the best AI tools for learning

You can now learn anything by using:

- Step-by-step guided learning
- Generate unlimited quizzes and flashcards
- Understand complex things w/ visuals and YT videos

Suitable for any topic you want to explore.

More below

1. Quiz generation

Gemini can now generate interactive quizzes on any topic.

- Start a new conversation
- Enter a prompt such as: “Generate a quiz to learn...”
- Gemini generates 10 questions

At the end, you can choose to generate new questions, analyze your weak points, or create flashcards.

2. Flashcards

You can generate sets of 25 flashcards... with audio!

Perfect for language learning or memorizing technical terms.

Example for vocabulary (audio on):

Read 6 tweets

Paul Couvert

@itsPaulAi

Aug 5

OpenAI has finally released GPT OSS 20B!!

This is probably the most powerful model you can run locally on a laptop.

→ Only 3.6B active parameters
→ Adjustable "Reasoning Effort"
→ Works with 16GB of RAM!

Quick steps to use it 100% free and offline:

You can run it using LM Studio:

1. Download LM Studio for your OS
(Windows, macOS or Linux)

2. In the search tab, type "GPT OSS 20B"

3. Download the recommended model