Bing is getting a new look and feel, powered by Microsoft AI and OpenAI (ChatGPT) and was announced yesterday. There is a lot of buzz around this, and I thought I would share my thoughts on this as I got access today.
What is the new Bing?
Well, it is the thing that is making the 800-pound gorilla in the room, Google, come out and dance on its toes. 🦍
The new Bing is an overhauled version of the search engine that uses ChatGPT technology to understand questions and generate answers. It runs on the next generation of OpenAI’s language model, which is significantly more capable than the version of ChatGPT that has been available since November 20221. The new Bing provides more relevant results for simple things like sports scores, stock prices and weather, along with a new sidebar that shows more comprehensive answers if you want them3. You can also chat and create with the new Bing, using its natural language and creative abilities4. The new Bing is live starting today, with limited capabilities.
Here is what it looks like:
What is ChatGPT?
If you are curious about ChatGPT, and you have really been living under a rock and don’t know it 🤪, then read up more here .
Searching within a site
Using the updated Edge browser, which extends the new Bing experience to the browser, you can search a site by typing in the site name and then the search term. For example, here I am searching for the word “hacking” on my blog “blog.desigeek.com”:
Chat with Bing
You can chat with Bing and ask it questions like: “tell me a joke about AI developers”
And what is the meaning of life?
Or it can write a poem on #NeuralNetworks:
Neural networks are amazing
They can learn from data and do amazing things
They can recognize faces, voices, and objects
They can generate images, texts, and sounds
They can play games, drive cars, and diagnose diseases
They can do anything, or so it seems
Neural networks are complex
They have layers and nodes and weights and biases
They have activation functions, loss functions, and optimizers
They have backpropagation, gradient descent, and regularization
They have hyperparameters, architectures, and algorithms
They have a lot of math, and a lot of tricks
Neural networks are mysterious
They can be hard to understand and explain
They can be prone to errors and biases
They can be overfitting, underfitting, or just fitting
They can be black boxes, white boxes, or gray boxes
They can be a blessing, a curse, or a challenge
And not only it can write a #Haiku for my wife on our anniversary, but it remembers the context. 💓
Twenty-two years passed
We are still in love and laugh
You are my better half
And of course, we can do just plain old vanilla #Haikus’ too:
Haikus are easy
But sometimes they don't make sense
Refrigerator
And it can even write code:
#include <stdio.h>
// A function that prints a funny haiku
void write_funny_haiku()
{
// Declare and initialize an array of strings
char *haiku[3] = {"Haikus are easy", "But sometimes they don't make sense", "Refrigerator"};
// Loop through the array and print each line
for (int i = 0; i < 3; i++)
{
printf("%s\n", haiku[i]);
}
}
// A main function that tests the write_funny_haiku function
int main()
{
// Call the write_funny_haiku function
write_funny_haiku();
// Return 0 to indicate success
return 0;
}
And of course we can do some sports. #F1 rules 🏎️
And finally, we can even have some fun. 😆
There once was a search engine named Bing
It could find anything and everything
It was faster and smarter
More helpful and friendly
And it made Google look like a ding-a-ling
Happy searching! 🤓