DEV Community: Alex Agboola

We Fixed Stack Overflow

Alex Agboola — Tue, 26 Nov 2024 16:44:42 +0000

Links:

As a junior developer, I’ve often turned to Stack Overflow for help, but I’ve noticed a growing discontent among my peers. Let’s dive into why many developers are becoming disenchanted with this once-revered platform and explore a promising alternative.

The Unwelcoming Atmosphere

When I first started coding, I was eager to join the Stack Overflow community. However, I quickly realized that asking questions as a newcomer can be intimidating. The platform, which should be a haven for learning, often feels like a hostile environment. Snarky comments and harsh downvotes without explanation are commonplace, leaving many of us feeling discouraged and hesitant to engage.

The strict moderation, while intended to maintain quality, sometimes goes overboard. I’ve seen questions closed as duplicates even when the linked answers were outdated or didn’t fully address the issue at hand. It’s frustrating to see genuine queries shut down without a fair chance for discussion.

Quality Concerns and Outdated Information

As I’ve progressed in my coding journey, I’ve noticed another issue: the prevalence of outdated information. Many popular answers date back to 2013 or earlier, which is practically ancient in the fast-paced world of technology. The difficulty in updating or adding new answers to old questions means that we’re often left with obsolete solutions.

Moreover, the focus on reputation points sometimes leads to unhelpful behavior. I’ve witnessed users racing to post quick, superficial answers just to gain points, rather than taking the time to provide comprehensive, well-thought-out responses.

The Inclusivity Problem

Perhaps the most concerning aspect is the lack of inclusivity on the platform. As a junior developer, I often feel that Stack Overflow caters more to experienced programmers. The perception of elitism can be off-putting, especially for those of us just starting our coding careers.

Even more troubling are the reports of unfriendliness towards women, people of color, and other marginalized groups in tech. A platform that should be uniting developers is instead reinforcing divisions within our community.

How We Fixed This

Recognizing these issues, a group of us junior developers decided to take action. We’ve formed a squad on daily.dev (which is a platform for developers) with the goal of creating a toxic-free alternative to Stack Overflow. Our platform prioritizes inclusivity, patience with newcomers, and up-to-date information.

We’re building a space where questions at all levels are welcomed and where constructive feedback is the norm. Our moderation system is designed to be fair and transparent, focusing on guiding users rather than penalizing them.

Conclusion

While Stack Overflow has undoubtedly been a valuable resource, it’s clear that the developer community needs something more. As we work on our alternative platform, we’re excited about the possibility of creating a truly inclusive and supportive environment for developers of all backgrounds and skill levels.

GPT-4o | This Changes The Game For Voice Assistants

Alex Agboola — Tue, 21 May 2024 11:01:44 +0000

Just last week, OpenAI launched its new flagship model, ChatGPT 4o, and it’s packed with features that are set to revolutionize the AI landscape. In a recent episode of my podcast, “AI with Alex,” I had the opportunity to discuss these advancements with Jonah, a software developer who is eager to transition into data engineering and machine learning. Our conversation shed light on how this new model is not only faster and more interactive but also more accessible to the general public.

The Good…

ChatGPT 4o brings several improvements over its predecessor, GPT-4.

Speed: One of the standout features is its speed. ChatGPT 4o can generate responses in as little as 200 milliseconds. Jonah and I agreed that this is a significant upgrade from GPT-4, which could sometimes take several seconds or even minutes to produce a response. This speed improvement is crucial for enhancing user experience, especially for those who rely on AI for real-time interactions.
Interactivity: The new model can see and hear, enabling more natural and human-like conversations. This leap forward makes it feel like you’re talking to a real person rather than an AI. Jonah pointed out that this feature could be particularly useful in various applications, from customer service to personal assistants.
User Interface: OpenAI has revamped the UI to make it look more like a modern text app with speech bubbles. This design choice makes the AI more accessible and user-friendly, moving away from the technical appearance that might intimidate non-tech-savvy users. Jonah noted that this shift is essential for broader adoption, as it allows a wider audience to benefit from AI technology.

…The Bad…

While ChatGPT 4o is a significant step forward, there are areas where it still has room for improvement.

Features Rollout: Not all features are available yet. Jonah mentioned that while the model offers more options to play around with, many features are still in the pipeline. Users will have to wait to fully experience everything ChatGPT 4o has to offer.
Accessibility Limits: Although the model is free for everyone, there are still limitations for free users compared to paying users. This means that while many can access the AI, those who can afford to pay will have a more enriched experience, which may create a disparity in usage.
Technical Dependency: As with all AI models, ChatGPT 4o is highly dependent on the quality of user prompts. A well-constructed prompt will yield better results, but vague or poorly phrased prompts might not produce the desired output. This dependency means users need to learn how to interact effectively with the AI to get the best results.

…And The Ugly (With Some Predictions)

The release of ChatGPT 4o signals a shift in the AI landscape that could have far-reaching implications.

AI Gadgets: Jonah and I discussed how this new model might render many AI gadgets obsolete. Why invest in additional hardware when your phone can offer the same, if not better, capabilities? This advancement might put a dent in the AI gadget industry, which often relies on novelty rather than practical utility.
Industry Impact: The rapid advancement of AI models like ChatGPT 4o could disrupt various industries. For instance, developers might find themselves relying more on AI for code generation and debugging, potentially reducing the need for human input. Jonah highlighted that this could lead to job displacement if not managed carefully.
Ethical Concerns for The Future: With great power comes great responsibility. The capabilities of ChatGPT 4o raise ethical questions about data privacy and AI regulation. Jonah and I agreed that while it’s exciting to see such advancements, it’s crucial to have frameworks in place to ensure that the rapid advancement of AI technology does not come at the expense of ethical considerations and privacy.

Conclusion

ChatGPT 4o marks a significant milestone in AI development. With its enhanced speed, interactivity, and accessibility, it has the potential to revolutionize how we interact with technology. Jonah’s insights highlighted the exciting possibilities and the importance of mindful advancement as we move towards an increasingly AI-driven future. This is a game-changer, and it will be interesting to see how it evolves and impacts our daily lives.

If you want to learn more about this topic, subscribe to my YouTube channel. This episode hasn’t been released yet, but you’ll be notified as soon as it’s available.

P.S. Want to hear a secret? This article was generated by ChatGPT 4o…

Goodbye Internet... For Now

Alex Agboola — Mon, 29 Apr 2024 20:00:00 +0000

If you couldn't tell already, I haven't been posting a lot of articles lately. This is because I haven't really gotten the time to do so.

The Problem

As you saw from my last article, I started a new podcast called AI With Alex on Spotify and YouTube. The show is basically about me discussing with various of guest about all things AI.

It was fun having conversations with AI experts about pretty much my favorite part of the whole thing.

Then… there was the editing part.

Even though I was using Riverside's editor (which made my editing time cut in half), I still spent hours on editing one episode. Then, I won't have time to even code.

Even if I had time, I would lose motivation to do pretty much anything after editing.

I want to write articles, but I just don't have the motivation and/or time.

The Solution…?

I decided to officially take a break from writing.

I normally code and write articles, but adding a whole weekly podcast to the mix is not feasible for me.

On May 20, 2024, I will start posting articles more frequently (hopefully).

Conclusion

To sum things up, I need a break. I will hopefully gain more time in the future. I will probably write about what I normally write about - AI, coding, tech news, etc.

Thanks for reading this article, I appreciate it.

AI With Alex | S1 Ep. 2 Coming Soon!

Alex Agboola — Wed, 10 Apr 2024 23:26:35 +0000

I excited to announce that S1 Ep. 2: Generative AI is coming soon!

Make sure to subscribe to Alex The Dev to be posted when its's released!

My New Podcast: AI With Alex

Alex Agboola — Sun, 07 Apr 2024 22:02:03 +0000

Hey everyone!

I'm happy to announce that I have now posted my first podcast: AI With Alex.

On the show, I discuss my opinion on the latest trends/news about AI, and the future of AI with AI experts.

Keep in mind that this is my first podcast ever, so feedback is appreciated.

If you want to listen to the podcast, here are some links:

YouTube

Spotify

If you want to be featured on my podcast:

Calendly

Calendly - Alex Agboola

calendly.com

DEVin | The Scary Future For Developers

Alex Agboola — Mon, 18 Mar 2024 18:07:49 +0000

(source for image)

This month on the 12th, the AI company Cognition AI showed to the world the first AI Software Engineer, Devin. Devin is the first AI that can not only have its own personal code editor and web browser but also does the process that a real software engineer would do. Seeing what Devin can do has fascinated me, but at the same time, I have also realized that I have heavily underestimated AI in the future and what that means for developers.

The Good...

Devin can be extremely helpful for developers in many ways.

1) Debugging

In one of the demos Cognition AI showed, a developer in the company showed how Devin can debug your code for you. They had a Git repository and had Devin come up with test cases and test the code for him. It turns out that the code had a bug and Devin debugged the code for him.

Devin debugs code by adding code that catches errors, for example, in Python, a print function could be used to detect any errors in Python code.

2) Self-Learning

Devin can self-learn, meaning for example, one developer trained Devin using a blog that she had found. Devin then learned from the blog and did the step-by-step process the blog had given. When Devin tested to finished code, it arrived to an error that the blog had. Devin debugged and fixed the code and outputted some pretty good results.

3) Performance

In the SWE-bench (Real World Software Engineering Performance) Devin has a huge (compared to other competitors) 13.86% (that means that this LLM (Large Language Model) can resolve real-world GitHub issues 13.86% of the time)! To put that into comparison, the AI in second place in terms if the SWE-bench is Claude 2 with only a 4.8% of solving a real-world Github issue.

...The Bad...

Everything that is first at something is going to be the worst in the area, what I mean is that Devin is at its worst, and will improve more and more over the years.

1) Speed

Depending on what Devin is coding, Devin can take minutes, hours, or even days! You could argue that a normal human software engineer could also take days, but compared to its competitors like ChatGPT and Llama, it's pretty slow.

2) Dependency on user's prompts

Like most AIs, Devin needs good prompts for good results. So giving Devin a 9-word sentence like:

Code an AI pet simulator in HTML and JS

Is not going to give you as good results if you would have given Devin a more detailed prompt.

3) Performance

Yes, Devin does have the best SWE-bench performance out of any AI out there, but it only solves 13.86% of real-world GitHub issues. What about the other 86.14%? Devin can not solve real-world Github issues 86.14% of the time, so your not going to be able to 100% automate your coding.

...and The Ugly

Devin right now might not be able to replace developers, but Devin does reveal a path we are heading towards that I never thought was possible.

AI taking jobs

I knew that AI has, is, and will take jobs from humans. Before, I thought developers didn't apply to this, after all, we are the ones who code the AI in the first place. But AI is already starting to replace developers. Developers are very dependent on AI; using it to debug their code, adding code snippets, or even completely coding for them.

Of course AI is definitely not perfect, so developers still need to code, but in the future, AI will be so advanced, I'm worried that not only will developers be so dependent on AI that AI is just doing developers’ jobs for them, but companies will start replacing developers with AI. After all, why pay over $100,000 per year per developer when you could pay $100 per year for unlimited AI.

ASI

Expert Ben Goertzel has predicted that AI will reach ASI (Artificial Super Intelligence) as early as 2027 (source). You could think of ASI as sentient AI or the singularity. Artificial Super Intelligence is where AI is so advanced that it has its own conciseness, its own emotions, and it surpasses human intelligence in all kinds of ways. In other words, ASI will be so advanced compared to humans, it would be a joke if you hired a human developer when ASI exist.

Conclusion

So in conclusion, Devin is awesome and is going to help developers, but it's not a major threat to developers right now. Devin has great potential, as it is the first AI software engineer, but we should as keep in mind because it's the first AI software engineer, it is also going to be the worst AI software engineer.

What Devin is, though, is a wake-up call to people who want to learn to code to do it now. 2024 is the year to learn how to code, and based on the exponential growth of AI and the abundant amount of junior and entry-level developers, this year might be your last chance. Read my article to learn more.

If developers don't want to get swept up in the AI tsunami, it's best that we, use AI to our advantage and instead of using AI to automate our coding we should use AI in our applications and websites, using APIs like OpenAI or Stability AI, or even creating your own like I did here.

How To Use AI To Create Your Own App (No Coding Knowledge Required)

Alex Agboola — Fri, 23 Feb 2024 23:35:42 +0000

Normally, if you want to create your own app, you would have to learn programming languages like Dart or C#, but we're going to use only HTML, CSS, and JavaScript. The best part is, you don't have to know how to code at all!

We are going to create this webapp for free this with only using 3 tools:

ChatGPT (any version is fine)
Virtual Studio Code (or any code editor)
Web into app.com

Web into app is a website where you can convert your HTML or website of your choice to an apk file so you can publish your app on platforms like Google Play Store or the App Store.

1) Getting the code from ChatGPT

ChatGPT is an AI chatbot that can do many things as long as you ask for text (or images if you are using GPT 4.0). These are the steps on how to sign up and obtain the code:

1) Create your own account

Go to OpenAI's website and click on the top right button that says "Try ChatGPT".

You should be taken to this screen:

Click the signup button and it should take you to this page:

Once you create your account, you should see something similar to this:

2) Generate the code

Now you are on the ChatGPT page, ask ChatGPT to code any website you would like to be an app using HTML, CSS, and JavaScript (make sure the website is responsive meaning it can be viewed properly on mobile devices)

Example Prompt

Code a simple note-taking website where users can take notes like a notebook. Make sure it is coded in only HTML, CSS, and JavaScript, and the website looks like a notebook. I should be able to see notes in each grid below the input box that includes the date that note was typed in and the actual note which is saved even after I refresh the website. This website should be responsive and tailored towards smartphones. I want all of the code in one HTML file, meaning that you should put style and script tags for CSS and JavaScript in your HTML code.

ChatGPT gave me this code:

<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Notebook App</title>
<style>
  body {
    font-family: Arial, sans-serif;
    margin: 0;
    padding: 0;
    background-color: #f0f0f0;
    display: flex;
    justify-content: center;
    align-items: center;
    height: 100vh;
  }

  .container {
    background-color: #fff;
    padding: 20px;
    border-radius: 10px;
    box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
    width: 90%;
    max-width: 400px;
  }

  input[type="text"] {
    width: calc(100% - 40px);
    padding: 10px;
    border: 1px solid #ccc;
    border-radius: 5px;
    margin-bottom: 10px;
  }

  button {
    padding: 10px 15px;
    background-color: #007bff;
    border: none;
    color: #fff;
    border-radius: 5px;
    cursor: pointer;
  }

  .note {
    border-bottom: 1px solid #ccc;
    padding: 10px 0;
  }

  .note:last-child {
    border-bottom: none;
  }

  .note-date {
    font-size: 12px;
    color: #888;
  }

  .note-content {
    margin-top: 5px;
    white-space: pre-wrap;
  }
</style>
</head>
<body>

<div class="container">
  <input type="text" id="noteInput" placeholder="Type your note here...">
  <button onclick="addNote()">Add Note</button>
  <div id="notesContainer"></div>
</div>

<script>
  function addNote() {
    const noteInput = document.getElementById('noteInput');
    const noteContent = noteInput.value.trim();
    if (noteContent === '') return;

    const date = new Date();
    const dateString = `${date.toLocaleDateString()} ${date.toLocaleTimeString()}`;

    const noteElement = document.createElement('div');
    noteElement.classList.add('note');

    const dateElement = document.createElement('div');
    dateElement.classList.add('note-date');
    dateElement.textContent = dateString;

    const contentElement = document.createElement('div');
    contentElement.classList.add('note-content');
    contentElement.textContent = noteContent;

    noteElement.appendChild(dateElement);
    noteElement.appendChild(contentElement);

    document.getElementById('notesContainer').appendChild(noteElement);

    // Save note to localStorage
    const notes = JSON.parse(localStorage.getItem('notes')) || [];
    notes.push({ date: dateString, content: noteContent });
    localStorage.setItem('notes', JSON.stringify(notes));

    noteInput.value = '';
  }

  // Load notes from localStorage
  window.onload = function() {
    const notes = JSON.parse(localStorage.getItem('notes')) || [];
    const notesContainer = document.getElementById('notesContainer');
    notes.forEach(function(note) {
      const noteElement = document.createElement('div');
      noteElement.classList.add('note');

      const dateElement = document.createElement('div');
      dateElement.classList.add('note-date');
      dateElement.textContent = note.date;

      const contentElement = document.createElement('div');
      contentElement.classList.add('note-content');
      contentElement.textContent = note.content;

      noteElement.appendChild(dateElement);
      noteElement.appendChild(contentElement);

      notesContainer.appendChild(noteElement);
    });
  };
</script>

</body>
</html>

(ChatGPT have generated a simple note-taking website)

It will take some trial and error, but you will eventually get the website you want.

2) Download the code

For this next step, I will be using Virtual Studio Code, but you can use any code editor as long as you can download the code as an HTML file.

1) Copy the code

It is very easy to copy the code quickly:

2) Go on your editor of chose

For me, it's Virtual Studio Code, but you can choose any code editor you like: it can even be online!

1) Create a folder (if in VSCode) and a HTML file

In VSCode, it's just as easy as clicking on an icon (but it can vary based on what code editor you use):

2) Paste ChatGPT's code

Once again, really easy to do. All you need to do is Ctrl + V (make sure to save your code if you are using VSCode using Ctrl + S):

3)(Not necessary on VSCode) Download the file

If you are not using Virtual Studio Code, you will need to download the HTML file (you don't need to download the file in VSCode because it should be there already). Make sure to compress your HTML file into a ZIP file, you will need it later.

3) Create your app

Go to Web into app.com and click "Get Started". It should take you to this screen:

Click on the "HTML Files" tab next to the currently selected tab "Online URL".

You should see something like this:

Now you can upload your ZIP file.

Your page should look similar to this:

You can now change the settings and personalize your app settings. You can press next.

Example Settings

Now, you will need to create an account. It's really easy: all you need to do is scroll down, click on "Register | FREE" and fill out the form:

After the site reloads, press the options you want (basically free or pay) and click "Make App".

You should see this screen once you clicked the button:

You should see your new app in your dashboard:

You can now download all files of your app by downloading:

4) Retrieving the apk file

We only need the apk file, and not the whole ZIP file.

1) Decompress the ZIP file to turn it into a folder.

2) Click on the folder and click on the "android" folder.

3) Copy your "app-release.apk" file and move it so the file is no longer in any folder.

You now have your own app that you can publish and use!

Conclusion

In conclusion, we were able to create an app without having to code or pay for anything.

Make sure to tell me in the comments what app you created using ChatGPT

How to code your own chatbot in Python

Alex Agboola — Sat, 17 Feb 2024 17:26:07 +0000

AI or Artificial Intelligence can be so advanced that it can be in self-driving vehicles capable of navigating through busy streets, personal virtual assistants who answer our questions and have conversations with us, and ways to systems capable of recognizing diseases in medical images. AI can be really complicated, even in the most simplest things like chatbots.

But there is a way to create your own chatbot without all of the fancy APIs or know a lot about AI. All you need is an email, and some basic knowledge in Python.

How To Create Your Own Chatbot

Creating your own chatbot is a lot simpler than you might imagine. It doesn't take thousands of lines to code; possibly less than 200 lines.

Nanohub makes it easy to create your own chatbot. A student created a template for you and all you have to do it tweak it slightly to personalizes your chatbot.

Don't worry if you don't know a lot of Python or even at all, the student made it easy to know what you are doing, and I will even help you too.

The Setup

The setup is most likely the hardest part of the whole process, so make sure to follow me step by step.

1) Make an account

Go to nanohub.org and create your account.

Your screen should look like this

Once you quickly make you account, you should be on the dashboard:

Your dashboard should look similar to this

2) Start a new session

Go to "My Tools" section on the most right-hand side of your dashboard.

Then click on the subsection "All Tools".

Now search and favorite (by clicking on the heart) this tool:

Jupyter Notebook (202105)

Click on Jupyter Notebook (202105) and it should take you to this screen:

When you click on the tool, it should take you to that screen

Now, click on Launch Tool (It should take a while)

3) Upload and start your tool

After awhile, you should be on this page:

You won't see any files if this is your first time on Nanohub. I have used it before, that's why you can see these files.

Now, click this link to download your chatbot template: Download File.

Once your file has finished downloading, click on the "Upload" button.

Once you have uploaded, you should see a new file on your screen:

Click on the file you have just uploaded and then you are officially done with the setup.

NOTE: Make sure to delete the error in the code:

The Personalization Part

The best part! You could spend hours or even days on this part, so below, I will give you some suggestions and how to code them.

1) Complete the TODOs

If you just want to do some simple tweaks, there are a bunch of "TODO" comments for you to complete. You don't have to do it all, but they help you know what to do and personalize.

Example

Code:

name = "The Best Bot"

2) Customize the responses

If you look deeper into the code, you will see some responses.

For example, this is one response to when you say "how are you?":

"how are you?": [ 
"I am feeling {0}".format(mood),
"I don’t ever wanna feel like I did that day, take me to the place I love, take me all the way",
"Eh, with the birds I'll share this lonley view, scar tissue that I wish you saw."
"{0}! How about you?".format(mood), ],

You can edit responses or even add some more responses that matches your chatbot.

Example

Code:

"what is 2 + 2?": [
    "2 + 2 = 4",
    "I don't know, {0}!".format(user_name),
    "Easy, 2 + 2 = 5!"
],

...

def user_intent(user_input_text):
    #if user_input_text is empty, no need to check for user intent.
    if len(user_input_text) == 0:
        return ""

    #this next command changes creates a list of lowercase words from input
    x_text = user_input_text.lower().split()
    #y_text is the intent keyword written exactly as in responses.
    y_text = ""

    #TODO: use this construct if you have many keywords for one intent.
    #the values in square brackets are your possible keywords
    if any(True for x in x_text if x in ["hello","hi", "hey", "greetings"]):
        y_text = "Hello"

    elif any(True for x in x_text if x in ["bye","goodbye", "exit", "done"]): 
        y_text = "Bye"

    #TODO: use this construct if you have only one keyword for one intent.
    elif "from" in x_text: 
        y_text = "Where are you from?"

    elif "born" in x_text: 
        y_text = "Where were you born?"

    elif "name" in x_text: 
        y_text = "what's your name?"

    elif "can you do" in x_text: 
        y_text = "What can you do?"

    elif "weather" in x_text: 
        y_text = "what's today's weather?"

    elif "robot" in x_text: 
        y_text = "Are you a robot?"

    elif "how are" in x_text: 
        y_text = "how are you?"

    elif "feeling" in x_text: 
        y_text = "how are you?"

    elif "why" in x_text: 
        y_text = "Why?"

    elif "good" in x_text: 
        y_text = "Good"

    elif "okay" in x_text: 
        y_text = "Okay"
     #The following code tells the chatbot "if the user says anything about math, do this
    elif "math" in x_text: 
        y_text = "what is 2 + 2?"
    #TODO: Add or remove as many elif as you need, leave this else intact.
    else: 
        y_text = ""

    return y_text

3) CHALLENGE: Add an API or a library in your code for a smarter chatbot

This is a little harder than the other two suggestions because I want to challenge my more intermediate audience.

The code already has a library imported:

#calling import random will allow Python to use commands in the random library
import random

...


The code in this cell will get a random message given the intent_keyword
#to send to the user associated with the keywords in the response
#if it cannot find the intent, it will return the default message

def respond(intent_keyword):

    if intent_keyword in responses: 
        bot_message = random.choice(responses[intent_keyword])

    else: 
        bot_message = random.choice(responses["default"])

    return bot_message

This code randomizes the responses. That's why you get a different response even if you ask the same question.

You can add another library or API into the code.

Example

Maybe try a weather library that gets the actual weather in your city.

Tell me in the comments what API/library you tried.

Conclusion

To sum things up, it is pretty easy to create your own chatbot using Nanohub, and you don't even need to know a lot of Python!

Should You Learn How To Code In 2024?

Alex Agboola — Wed, 31 Jan 2024 11:19:25 +0000

source

This has been a question of mine for a couple of days now. With the emergence of AI and the abundance of junior developers, it can be easy to re-think wanting to become a developer.

Should You Be a Developer?

Being a developer is a lot more than coding simple Python syntax or adding a cool h1 tag to a website. I can’t answer this question for everyone, sometimes it just boils down to “Do I even want to be a developer?”.

The Pros

High demand

There is a high demand for developers because, after all, the shift towards technology, it’s almost impossible to create a business or company without a website or app.

Great pay

You can expect to get paid (as a junior developer in the US) $70,000 to $90,000.

Remote work

Because most developers spend most of their time on their computers, most developers can work from home.

Creativity

It is a requirement to be creative if you want to be a developer. As I said in my article:
Sketch2Code | Is The Need For Web Developers Dying?
I said that the main reason AI is not taking web (or really any) developers’ jobs is because of originality and creativity. AI is just a bunch of algorithms, so it’s not like AI can create 100% original and creative websites as I said in my article:
ChatGPT SUCKS At Coding Websites

The Cons

Repetition

Debugging is essentially 90% of coding, which can be repetitive and lead to burnout.

Work-life balance

As a junior developer (especially for start-ups), you will work late nights and grueling hours.

How to be a web developer

After deciding if you want to be a developer, you have to figure out how you will be a developer.

How I Would Be a Full-Stack Developer (If I Could Start Over)

Don’t worry if you want to be a front-end developer or if you want to lean more into the back-end; I will label if you need to learn some things front-end or back-end.

The Roadmap (In order):

Learn the Front-End

-HTML (Front-End)
-CSS (Front-End)
-JavaScript (Front-End)
-JavaScript’s DOM (Front-End)
-APIs (Front-End)

-Learn how to use the Terminal

Learn the Back-End

-Node.JS (Back-End)
-The database basics (Back-End)
-React.JS (Front-End)
-TypeScript (Front-End)
-Learn Networks
-Learn how to use Cloud
-Learn about security
-Learn SSR

Conclusion

In conclusion, I think being a developer is a great idea.

It’s better to start now than later, because more and more people are starting to learn how to code and there are lots of junior developers, and the more junior developers, the more money the company wastes.

Let me elaborate. See, when a company hires someone, they need someone to teach you things. Not only is that company paying you to basically do nothing, they are also spending their time and energy with you until you are ready. This might not apply for every company, but you get my point. Companies are becoming very weary when it comes for junior developers, so you will need to stand out.

There are many ways to learn how to code, you can use platform like YouTube and Freecodecamp (which as both helped me a ton), you can pay for some classes or courses, or you can go to college and learn there. There are many ways to learn how to code, sometimes they take days, weeks, months, or even years depending on what you take.

Suggestions

If you have no idea what you want to do, here are some free and self-paced suggestions to jumpstart your coding career:
Freecodecamp.org
Coursera
Codecademy
PluralSight

The Future of AI: Multimodal AI Models

Alex Agboola — Sun, 07 Jan 2024 17:06:55 +0000

(source)

You've probably seen words like Machine Learning and Multimodal AI Models but aren't sure what they mean. It can be hard to fully know the technical terminology with today's emerging advanced AI models like ChatGPT or with AI models already integrated into our lives like virtual assistants Siri or Alexa. Today's article is on what is Multimodal AI Models and how they change our everyday lives.

What Are Multimodal AI Modals

Multimodal AI models are AI models that can process and interpret multiple types of data input at a time like audio, text, images, videos, and more.

For example, ChatGPT 4 can analyze and create images, so let's say I have a picture of a beach, and I ask ChatGPT:

Tell me what the weather might be in this picture.

ChatGPT combined different types of information – like pictures and text – to tell me what it thinks is the weather.

Why are Multimodal AI Models important?

Why are Multimodal AI Models so important? Combining different types of data can give you a more complete understanding of a topic, or in other words, ChatGPT can be your researcher. Instead of going through hundreds of websites on Google, you only need to type one prompt and get all you need in one convenient place.

Real-world examples of Multimodal AI Models

(source)

One great example we hear from Google a lot is their Gemini AI. I wrote an article all about it here. The article was about how Google has released Gemini 1.0, a multi-modal system that combines image, text, speech, and numerical data types to perform better results. I compared ChatGPT 4.0 with Bard's new AI, Gemini Pro, to test their natural language understanding and response capabilities.

Another fascinating example is GitHub Copilot. GitHub Copilot uses the ChatGPT-3 model. GitHub Copilot is an AI tool in collaboration with GitHub and OpenAI to help developers by autocompleting code.

Conclusion

In conclusion, multimodal AI models have revolutionized data processing by allowing various data types - such as audio, text, images, and videos - to be processed simultaneously. Now, you have at least an understanding of multimodal AI models and maybe overall AI terminology.

Trends of 2023 and Predictions on 2024 | The Industry Is Changing Drastically

Alex Agboola — Sat, 30 Dec 2023 22:00:59 +0000

(image from: an article)

2023 has been a fascinating year. We have seen how big AI has affected web development and our lives. ChatGPT 4.0 has been a very impactful chatbot acquiring knowledge and machine-learning upgrades. This article is not only a recap of the intriguing year 2023, but I will also talk about mine and other people's predictions of 2024.

Trends Of 2023

(image from: an article)

Here are my top 5 trends that have happened in 2023:

1. Artificial Intelligence Integration

AI (for obvious reasons) wasn't a surprise on this list. The one feature I and many bloggers have seen this year is how AI is integrated into websites and used for likewise customer support.

Yes, this idea of adding AI customer support is not new, and I have talked about it in my other blog earlier here. We have seen AI chatbots like ChatGPT become more intelligent and more capable, and I think these are the reasons why this topic deserves to be on this list.

2. Progressive Web Apps (PWAs)

PWAs are a trending thing this year and maybe even next year. Progressive Web Apps or PWA are simple websites focused on user experience and functionality, for example, a calculator or a weather application.

Why is it trending? Well, PWAs are very similar to native apps that have offline capabilities and fast loading times. They aren't heavy, so they are affordable for developers, making them very popular. They also offer amazing user experience, making it a very accessible tool as well.

3. Low-Code/No-Code Development

Low-code or No-Code Development has been a trend for a while, and it'll be one for a long time. Applications like Webflow and WordPress are broadening the definition of being a developer; you don't need to know how to code to become an extraordinary developer!

4. Cybersecurity Enhancements

As tech becomes more sophisticated, so will cyber attacks like viruses or hacker technology. Because of that, the need for more advanced security is growing.

Developers will need to apply things like anti-viruses and additional security measures, encompassing advanced sign-up requirements or encryption.

5. JavaScript's Dominance

I'm not surprised JavaScript made it on the list. It is one of if not the most popular language in web development, and it's no surprise it is going to continue to be like that in the future.

With JavaScript's endless amount of popular libraries, how easy it is to learn, and how much of a demand it is, you can only know HTML, CSS, and Javascript (vanilla and libraries)and already 80% completed with your full-stack journey.

Predictions for 2024

(image from: an article)

2024 is going to be a year full of fun! Here are my 5 predictions I have made for next year:

1. Quantum Computing in Web Development

Quantum Computing in web development means websites will load faster, as the author, Abid Salahi, describes in his article: "...websites that load in milliseconds, capable of handling immense data loads with no lag".

Quantum Computing is a game-changer if it's becoming a trend in 2024, but it won't be to you if you don't even know what it means!

What Even Is Quantum Computing

Quantum computing is a real-life, incredible piece of technology that uses quantum-like tech. Unlike normal computers that use bits (0s and 1s), quantum computers use quantum bits or qubits. This allows qubits to be in multiple states at the same time.

2. Dark Mode

Dark Mode is not only good at battery, better on the eyes, it's just looks cool. I and many people use dark mode on almost every website. Dark mode has been a thing this year and it doesn't look like it will stop. In fact, over 60% of users world-wide said they use dark mode.

What Is the Future For Dark Mode?

One example is websites will be able to detect what time it is for the user (websites can do this already) and change the mode based on the time. So when it is in the afternoon, it will be light mode, then at night or early in the morning, dark mode will turn on.

3. Server-less Computing

Server-less Computing makes one less thing for developers to worry about. Server-less Computing doesn't actually mean no servers; it just means developers can focus on code and not server management.

Other Perks Of Server-less Computing

Cost-efficient
Takes less time to make
Very scalable

4. AR in Websites

Yep, Augmented Reality in web development.

Websites like Amazon and Walmart have this feature where you can see the product you want to buy in real time. Meta has also added this feature in their Meta Quest VR headsets.

AR in websites can be a real game-changer, both literally and metaphorically.

For example, Scratch, which is a platform made for kids and beginners to learn the basics of coding using block-based programming, has this feature where you can program a game using AR features:

5. AI

AI will be a revolutionary in 2024.

From helpful code snippets to AI-generated designs, AI has and will change the industry drastically.

I have even written an article on how helpful AI has been and will be here.

For example, AI will be crucial for optimizing websites for search engines, especially voice searches. As people use voice assistants like Google Assistant and Siri, it becomes more important for websites to have a high SEO. Voice search optimization impacts SEO by changing how content is discovered and ranked on search engines like Google Chrome and Safari. AI can help with that.

Conclusion

2024 will be fun. Yes, these are only predictions, and these predictions may not happen, but I believe that they are true.

As we wrap up an awesome year in 2023, it's clear that the web development industry has majorly changed with improvements on AI, especially with the creation of ChatGPT 4.

In the year 2024, we will see major changes in web development. These changes include:

-the integration of quantum computing
-the rise of dark mode
-server-less computing
-augmented reality
-artificial intelligence

These trends will improve how users interact with websites.

Sketch2Code | Is The Need For Web Developers Dying?

Alex Agboola — Thu, 28 Dec 2023 14:32:03 +0000

Sketch2Code is an AI that can convert a quick sketch of a website to HTML code. This AI is not new. Microsoft has released this incredible AI in late 2019. After watching some YouTube videos on AI, I started to think, is the need for web developers dying?

Short-Term

Short-term, I don't think AI will kill the need for web developers. Even with the most powerful AI now (ChatGPT and Sketch2Code), they are more of a tool than a replacement. When I say short-term, I don't mean one year or two years; I am saying five years. But that can quickly change based on how AI continues to improve.

For example, I asked ChatGPT yesterday to generate a website based on a screenshot I took:

What I wanted ChatGPT 4 to code:

What ChatGPT 4 generated:

This AI (A custom ChatGPT), did a decent job. It was meant to lay the foundation of your screenshot so you can do the rest. As I said, as a tool and not a replacement.

Long-Term

In the long term, there will be changes to web development and overall coding. For example, If Sketch2Code can code a website for you with a simple sketch, web developers won't need to code as much.

AI is a lot of things: our code helper, our co-pilot, and even our fridge! As more and more AI is integrated into our lives, so is the demand for AI. AI is only improving and humans are not.

As AI continues to get smarter and smarter, people are becoming more obsolete. Why be a photographer with expensive cameras and years of training when AI can generate images with a few words, why become a musician, spending lots of money on instruments and classes when you can press "generate" to make music for you? Why become a programmer when AI tools like ChatGPT can code for you?

These are the reasons why I think in the long term, AI will do our jobs for us, and this is only the beginning.

What I think

I know web development is not dying. This year, more than one million unfilled spots need to be filled by developers!

The way I see it, ChatGPT (and other AI tools), just like NFTs, will die out eventually. I'm not saying AI is dying. It's thriving! I'm saying that (not so soon!) ChatGPT and other AI tools will get overtaken by more, smarter, and overall better AI. AI, after all, is a tool and not a replacement.

It is a great time to be a web developer! AI is not everything, but it is a lot of things.

Conclusion

AI isn’t everything. I've heard people say “AI is the future and that’s all we should focus on.” or “Why be a web developer when there are AI tools that can make websites in seconds?”. These claims are not accurate.

I went to the website, “Will Robots Take My Job” and searched for web developers the results were rather shocking. Some people thought AI would take my job! W.R.T.M.J runs on votes from users around the world, so the results might be biased, inaccurate, or someone might be trolling, so it is not a very reliable tool.

If there is one thing that might make me keep my job is that when you are a web developer, you need originality. “StackOverflow Ctrl + C, Ctrl + V ‘developers’” won’t get a job because they won’t know how to code. That’s one thing AI isn’t good at. Robots are copy-and-paste machines!