Introduction

Meta AI from Facebook is one of the last big technology giants’ contenders in the AI battle. In our first article, we created a demo about ChatGPT. Secondly, we talked about Bing from Microsoft, who is now Copilot. Thirdly, we mentioned Bard from Google, which is Gemini now.

However, Mark Zuckerberg and Facebook did not want to be out of the AI party. Now we have Meta AI incorporated into WhatsApp or in Facebook. We can also use Meta AI in the browser. In this article, we will talk about this new technology.

Meta AI history

Meta AI was created by the Facebook Artificial Intelligence Research (FAIR). This is the division of Meta Platforms (Facebook) in charge of the artificial intelligence research. In addition, Meta AI was founded on December 11, 2015 as Facebook Artificial Intelligence Research (FAIR). FAIR started with machine learning and artificial intelligence to understand intelligence and make machines significantly more intelligent. After that, they worked on face recognition, tagging in photographs, and personalized feed recommendations. In October 2021, Facebook rebranded itself as Meta Platforms, and focused on the "metaverse" and virtual reality environments.

Currently, Meta is presenting the Meta AI to compete with ChatGPT, Gemini, Copilot, Deepseek, and other competitors.

Getting Started

Let’s start with a conversation with Meta AI.

Daniel: Hello. What are you?

Meta AI: Hello! I'm Meta AI, a friendly AI assistant. I can help answer questions, provide information, generate text, and even create images. I'm constantly learning and improving, so please bear with me if I make any mistakes. How can I assist you today?

Daniel: Are you based in ChatGPT or are you a completely different technology?

We are both chatbots, but I was created by Meta, while ChatGPT was developed by OpenAI. Our training data, language understanding, and overall tone and purpose are unique, so we each have different strengths and capabilities.

Can Meta AI have access to the internet?

Daniel: Can you navigate on the internet to get current data?

Meta AI: I can't browse the internet or access real-time data. My responses are based on the data I was trained on, which is a massive dataset that was available to me when I was trained. However, my training data only goes up until 2022-2023, so I may not have the most up-to-date information on very recent events or developments.

Daniel: What are your strengths compared with Copilot and ChatGPT?

Meta AI:

We all share some similarities, but I've been designed to be more conversational, concise, and helpful in a broader range of tasks and topics. Here are some of my strengths:

1. Conversational dialogue: I'm trained to engage in natural-sounding conversations, using a more casual tone and including relevant questions to clarify context.
2. Concise responses: I aim to provide clear and direct answers, focusing on the most important information and avoiding unnecessary elaboration.
3. Task-oriented: I can assist with a wide range of tasks, from generating creative content and providing definitions to solving math problems and translating languages.
4. Knowledge base: While not exhaustive, my training data covers a vast range of topics, including but not limited to history, science, entertainment, culture, geography, and more.
5. Multilingual support: I can understand and respond in multiple languages, making me more accessible to users worldwide.
6. Continuous learning: My training data is constantly updated and expanded to keep my knowledge up-to-date and accurate.

Keep in mind that each AI model has its unique strengths and weaknesses. If you have specific needs or preferences, you may find that one model works better for you than others.

Meta AI opinion about SQL Server 2022

Daniel: What is your opinion about SQL Server 2022?

Meta AI: SQL Server 2022 is a powerful relational database management system (RDBMS) that offers numerous enhancements and improvements over its predecessors. Here are some key features and benefits:

Key Features

1. Improved Performance: SQL Server 2022 introduces several performance enhancements, including improved query optimization, faster data processing, and better resource utilization.
2. Enhanced Security: The new version includes advanced security features, such as Azure Active Directory (AAD) authentication, encryption, and access control.
3. Data Virtualization: SQL Server 2022 allows you to integrate data from various sources, including Azure Blob Storage, Azure Data Lake Storage, and other databases.
4. Cloud-Native Capabilities: The database engine is designed to work seamlessly with cloud environments, providing features like elastic scaling, automated patching, and backup.
5. Improved Analytics: SQL Server 2022 includes advanced analytics capabilities, including machine learning, data warehousing, and business intelligence.

Benefits

1. Faster Insights: With improved performance and analytics capabilities, you can gain faster insights from your data.
2. Enhanced Collaboration: SQL Server 2022 enables seamless collaboration between developers, data scientists, and business users.
3. Increased Agility: The database engine provides a flexible and scalable platform for developing and deploying applications.
4. Better Data Governance: With advanced security and access control features, you can ensure that your data is secure and compliant with regulatory requirements.

Overall, SQL Server 2022 is a robust and feature-rich database management system that can help organizations unlock insights, improve collaboration, and drive business success.

Do you believe that SQL Server on premises will stop and everything will migrate to the cloud?

While cloud adoption is increasingly popular, I don't think SQL Server on-premises will completely disappear. Here's why:

Reasons for On-Premises Persistence

1. Data Sovereignty: Some organizations, especially those in regulated industries, require strict control over their data and may not be comfortable hosting it in the cloud.
2. Security Concerns: On-premises environments can provide an additional layer of security, as data is stored within the organization's own infrastructure.
3. Legacy Systems: Many organizations have invested heavily in on-premises infrastructure and may not be able to migrate their legacy systems to the cloud easily.
4. Low Latency Requirements: Certain applications, such as real-time analytics or high-frequency trading, require ultra-low latency, which may be difficult to achieve in a cloud environment.

Hybrid Approach

1. Cloud-First Strategy: Many organizations are adopting a cloud-first strategy, where new applications and workloads are deployed in the cloud, while existing on-premises workloads are maintained.
2. Hybrid Cloud: Some organizations are using a hybrid cloud approach, where they use a combination of on-premises and cloud infrastructure to meet their needs.

Microsoft's Strategy

Microsoft has stated that they will continue to support and invest in SQL Server on-premises, while also providing a clear path for customers to migrate to the cloud when they're ready.

In summary, while the cloud will continue to grow in popularity, I don't think SQL Server on-premises will completely disappear. Instead, organizations will adopt a hybrid approach, using a combination of on-premises and cloud infrastructure to meet their needs.

Create some T-SQL Code with Meta AI

Me: It is not bad, let’s take a look at the code created. Also, can you generate some T-SQL tables with data? Please apply best practices. Based on the tables, create a view and a stored procedure.

Meta AI: Here's an example of T-SQL tables with data, a view, and a stored procedure, following best practices:

Tables

SQL

-- Create schema
CREATE SCHEMA Sales
GO
-- Create tables
CREATE TABLE Sales.Customers (
CustomerId INT PRIMARY KEY IDENTITY(1,1),
FirstName NVARCHAR(50) NOT NULL,
LastName NVARCHAR(50) NOT NULL,
Email NVARCHAR(100) UNIQUE NOT NULL,
CreatedDate DATETIME DEFAULT GETDATE()
);
CREATE TABLE Sales.Orders (
OrderId INT PRIMARY KEY IDENTITY(1,1),
CustomerId INT NOT NULL,
OrderDate DATETIME DEFAULT GETDATE(),
Total DECIMAL(10, 2) NOT NULL,
CONSTRAINT FK_Orders_Customers FOREIGN KEY (CustomerId) REFERENCES Sales.Customers(CustomerId)
);
CREATE TABLE Sales.OrderItems (
OrderItemId INT PRIMARY KEY IDENTITY(1,1),
OrderId INT NOT NULL,
ProductName NVARCHAR(100) NOT NULL,
Quantity INT NOT NULL,
UnitPrice DECIMAL(10, 2) NOT NULL,
CONSTRAINT FK_OrderItems_Orders FOREIGN KEY (OrderId) REFERENCES Sales.Orders(OrderId)
);

Data

SQL

-- Insert data
INSERT INTO Sales.Customers (FirstName, LastName, Email)
VALUES
('John', 'Doe', 'john.doe@example.com'),
('Jane', 'Doe', 'jane.doe@example.com'),
('Bob', 'Smith', 'bob.smith@example.com');
INSERT INTO Sales.Orders (CustomerId, Total)
VALUES
(1, 100.00),
(1, 200.00),
(2, 50.00),
(3, 75.00);
INSERT INTO Sales.OrderItems (OrderId, ProductName, Quantity, UnitPrice)
VALUES
(1, 'Product A', 2, 25.00),
(1, 'Product B', 1, 50.00),
(2, 'Product C', 3, 33.33),
(3, 'Product D', 1, 50.00),
(4, 'Product E', 2, 18.75);

View:

SQL

-- Create view
CREATE VIEW Sales.CustomerOrders
AS
SELECT
C.CustomerId,
C.FirstName,
C.LastName,
O.OrderId,
O.OrderDate,
O.Total
FROM
Sales.Customers C
INNER JOIN
Sales.Orders O ON C.CustomerId = O.CustomerId;

Stored Procedure:

SQL

-- Create stored procedure
CREATE PROCEDURE Sales.GetCustomerOrders
@CustomerId INT
AS
BEGIN
SELECT
O.OrderId,
O.OrderDate,
O.Total
FROM
Sales.Orders O
WHERE
O.CustomerId = @CustomerId
ORDER BY
O.OrderDate DESC;
END;
GO

To execute the stored procedure:

SQL

EXEC Sales.GetCustomerOrders @CustomerId = 1;

Me: I tested the code. Also, I created the objects and tested the data. The code worked fine.

Meta AI in WhatsApp

Now, you can talk to Meta AI using your WhatsApp. Also, you can use the search option to ask Meta AI or press the Meta AI icon to use this service:

It works in the same way.

Daniel: Also, create a T-SQL query to detect the space used by a database.

Meta AI: Here is a T-SQL query that detects the space used by a database:

SELECT
db.name AS DatabaseName,
CAST((SUM(file_size) * 8192.0) / 1048576.0 AS DECIMAL(10, 2)) AS TotalSpaceUsedMB
FROM
sys.master_files file
INNER JOIN
sys.databases db ON file.database_id = db.database_id
WHERE
db.name = 'YourDatabaseName'
GROUP BY
db.name

Replace 'YourDatabaseName' with the name of the database you want to check.

This query works by:

1. Joining the sys.master_files and sys.databases system views to get the file size and database name.

2. Filtering the results to the specified database.

3. Grouping the results by database name.

4. Calculating the total space used in megabytes (MB).

Note: The file_size column in sys.master_files is in units of 8192 bytes (8KB), so we multiply by 8192.0 and then divide by 1048576.0 to convert to megabytes.Drawing with Meta AI

Also, you can create images with Meta AI in your WhatsApp or browser. However, depending on your country, this feature may be restricted.

Drawing in Meta AI

Me: Please draw a corrupted database.

Meta AI:

Me: Mmmm…Can you generate a video of a database flying?

Meta ai:

Daniel: It just created an image. It does not look like a database.

Conclusion

To conclude we can say that meta AI is currently similar to the competitors. However, if it is fully integrated to Facebook, Instagram, and WhatsApp, it will be really useful for our daily tasks.

Also, it will be a great assistant in the long run if it can understand our voice and do some tasks automatically.