AI to explain complex things to a second grader using GPT-3.

AI to explain complex things to a second grader using GPT-3.

So, I have often experienced in interviews the interviewer asks to explain hard topics in a form that a child can understand.So, I thought let's make an AI for that and here we are.

So lets get some knowledge about GPT-3 and text-davinci-002 engine:

GPT-3 models can understand and generate natural language. There four main models with different levels of power suitable for different tasks. Davinci is the most capable model, and Ada is the fastest.

While Davinci is generally the most capable, the other models can perform certain tasks extremely well with significant speed or cost advantages. For example, Curie can perform many of the same tasks as Davinci, but faster and for 1/10th the cost.

Now that we that have some knowledge on GPT-3. Lets get started.

First the installs:

I am using Colab so the line will have a ! at start if you are using your local system just paste this in your terminal(win+r,cmd,Enter) without the ! and press enter.

Now, lets get started with the imports:

Lets now get our API key from OpenAI API site:

Step 1:

Go to OpenAI API site and Sign Up

Step 2:

Go to View API keys

Step 3:

Click on create new key

Now after creating the key create a .env file and put it in the same folder as the code.

Now lets pull that hidden key to our python program:

Lets get the prompt input from the user and synthesis it for making a perfect input in the text-davinci-002 model:

“Summarise this for a second-grade student:\n” this part is really important as GPT-3 can understand language and it will work better if you specify its task in the prompt.

Now lets finally setup the text-davinci-002 model:

There are the definitions of what each of the attributes mean

Temperature:

Max Tokens:

Top_P:

Frequency Penalty:

Presence Penalty:

Now lets print the output:

And with that the code is done!!

Lets see some outputs:

So, For this lets summarise the full text contents of my previous article:

So the input is:

So, two weeks ago I decided to make an AI to make Art and it was working beautifully then I was like why not make one for animation and here we are.

So for that lets first get a basic idea of how a animation works.

As you can see in the above image animations constitutes of many still images called Frames and Key change points called Keyframes.

Now with the basic knowledge of animation and the basic knowledge of image generation lets get started for the basic method. If wanna learn more about image generation go to my previous article on it:

Output:

Here you go lil Kid: Somebody made an AI that can make art, and then they decided to make one that can make animations. Animations are made up of lots of still images called frames, and there are keyframes which are important change points.

Lets Try teaching kids some Quantum Physics🤣

The input:

Quantum mechanics is a fundamental theory in physics that provides a description of the physical properties of nature at the scale of atoms and subatomic particles. It is the foundation of all quantum physics including quantum chemistry, quantum field theory, quantum technology, and quantum information science

The Output:

Here you go lil Kid: Quantum physics is the study of how matter and energy work at the most fundamental level. Scientists who study quantum physics are trying to understand the building blocks of nature and how they behave. Quantum physics can help us understand things that happen on a very small scale, like electrons and photons, but it also explains things

Hehe make one for yourself and enjoy explaining complex things to your lil brothers , sisters and cousins.

If you liked this article a follow in medium is appreciated 😁

Here is the Colab notebook:

For more stuff check out my GitHub:

Follow me on Twitter for my day to day AIML research updates:

Help me with my college funds (totally optional but appreciated a lot):

Thanks for reading, See ya guys net week 👋🏼