On today’s episode, we chat with Marcos Grappeggia, the product manager for Duet, an AI-powered assistant that can help you craft code by suggesting snippets—even full functions—as you write. Grappeggia explains why he thinks tools like this will augment, but not replace, the human developers at work today.

Episode notes:

Interested in trying Duet? You can get on the waitlist here.

You can learn more about tuning and deploying your own version of Google’s foundation models in their Generative AI studio.
If tuning a model sounds like a stretch, you can head to Model Garden, where a wide selection of open-source and third-party models are available to try.

TRANSCRIPT

The post Pair programing? We peek under the hood of Duet, Google’s coding assistant. (Ep. 580) appeared first on Stack Overflow Blog.

While the field is still developing fast, and factual errors, known as hallucinations, remain a problem for many LLM powered chatbots, a growing body of research indicates that a more guided, auto-regressive approach can lead to better outcomes.

This gets really interesting when applied to the world of software development and CI/CD. Most developers are already familiar with processes that help automate the creation of code, detection of bugs, testing of solutions, and documentation of ideas. Several have written in the past on the idea of self-healing code. Head over to Stack Overflow’s CI/CD Collective and you’ll find numerous examples of technologists putting this ideas into practice.

When code fails, it often gives an error message. If your software is any good, that error message will say exactly what was wrong and point you in the direction of a fix. Previous self-healing code programs are clever automations that reduce errors, allow for graceful fallbacks, and manage alerts. Maybe you want to add a little disk space or delete some files when you get a warning that utilization is at 90% percent. Or hey, have you tried turning it off and then back on again?

Developers love automating solutions to their problems, and with the rise of generative AI, this concept is likely to be applied to both the creation, maintenance, and the improvement of code at an entirely new level.

More code requires more quality control

The ability of LLMs to quickly produce large chunks of code may mean that developers—and even non-developers—will be adding more to the company codebase than in the past. This poses its own set of challenges. 

“One of the things that I’m hearing a lot from software engineers is they’re saying, ‘Well, I mean, anybody can generate some code now with some of these tools, but we’re concerned about maybe the quality of what’s being generated,’” says Forrest Brazeal, head of developer media at Google Cloud. The pace and volume at which these systems can output code can feel overwhelming. “I mean, think about reviewing a 7,000 line pull request that somebody on your team wrote. It’s very, very difficult to do that and have meaningful feedback. It’s not getting any easier when AI generates this huge amount of code. So we’re rapidly entering a world where we’re going to have to come up with software engineering best practices to make sure that we’re using GenAI effectively.”

“People have talked about technical debt for a long time, and now we have a brand new credit card here that is going to allow us to accumulate technical debt in ways we were never able to do before,” said Armando Solar-Lezama, a professor at the Massachusetts Institute of Technology’s Computer Science & Artificial Intelligence Laboratory, in an interview with the Wall Street Journal. “I think there is a risk of accumulating lots of very shoddy code written by a machine,” he said, adding that companies will have to rethink methodologies around how they can work in tandem with the new tools’ capabilities to avoid that.

We recently had a conversation with some folks from Google who helped to build and test the new AI models powering code suggestions in tools like Bard. Paige Bailey is the PM in charge of generative models at Google, working across the newly combined unit that brought together DeepMind and Google Brain. “Think of code produced by an AI as something made by an “L3 SWE helper that’s at your bidding,” says Bailey, “and that you should really rigorously look over.” 

Still, Bailey believes that some of the work of checking the code over for accuracy, security, and speed will eventually fall to AI as well. “Over time, I do have the expectation that large language models will start kind of recursively applying themselves to the code outputs. So there’s already been research done from Google Brain showing that you can kind of recursively apply LLMs such that if there’s generated code, you say, “Hey, make sure that there aren’t any bugs. Make sure that it’s performant, make sure that it’s fast, and then give me that code,” and then that’s what’s finally displayed to the user. So hopefully this will improve over time.”

What are people building and experimenting with today?

Google is already using this technology to help speed up the process of resolving code review comments. The authors of a recent paper on this approach write that, “As of today, code-change authors at Google address a substantial amount of reviewer comments by applying an ML-suggested edit. We expect that to reduce time spent on code reviews by hundreds of thousands of hours annually at Google scale. Unsolicited, very positive feedback highlights that the impact of ML-suggested code edits increases Googlers’ productivity and allows them to focus on more creative and complex tasks.”

“In many cases when you go through a code review process, your reviewer may say, please fix this, or please refactor this for readability,” says Marcos Grappeggia, the PM on Google’s Duet coding assistant. He thinks of an AI agent that can respond to this as a sort of advanced linter for vetting comments. “That’s something we saw as being promising in terms of reducing the time for this fix getting done.” The suggested fix doesn’t replace a person, “but it helps, it gives kind of say a starting point for you to think from.”

Recently, we’ve seen some intriguing experiments that apply this review capability to code you’re trying to deploy. Say a code push triggers an alert on a build failure in your CI pipeline. A plugin triggers a GitHub action that automatically send the code to a sandbox where an AI can review the code and the error, then commit a fix. That new code is run through the pipeline again, and if it passes the test, is moved to deploy. 

“We made several improvements in the mechanism for the retry loop so you don’t end up in a weird scenario, but that’s the essential mechanics of it,” explains Calvin Hoenes, who created the plugin. To make the agent more accurate, he added documentation about his code into a vector database he spun up with Pinecone. This allows it to learn things the base model might not have access to and to be regularly updated as needed. 

Right now his work happens in the CI/CD pipeline, but he dreams of a world where these kind of agents can help fix errors that arise from code that’s already live in the world. “What’s very fascinating is when you actually have in production code running and producing an error, could it heal itself on the fly?” asks Hoenes. “So you have your Kubernetes cluster. If one part detects a failure, it runs into a healing motion.” 

One pod is removed for repairs, another takes its place, and when the original pod is ready, it’s put back into action. For now, says Hoenes, we need humans in the loop. Will there come a time when computer programs are expected to autonomously heal themselves as they are crafted and grown? “I mean, if you have  great test coverage, right, if you have a hundred percent test coverage, you have a very clean, clean codebase, I can see that happening. For the medium, foreseeable future, we probably better off with the humans in the loop.”

Pay it forward: linters, maintainers, and the never ending battle with technical debt

Finding things during CI/CD or addressing bugs as they arise is great, but let’s take things a step further. You work at a company with a large, ever-growing code base. It’s fair to assume you’ve got some level of technical debt. What if you had an AI agent that reviewed old code and suggested changes it thinks will make your code run more efficiently. It might alert you to fresh updates in a library that will benefit your architecture. Or it might have read about some new tricks for improving certain functions in a recent blog or documentation release. The AI’s advice arrives each morning as pull requests for a human to review. 

Itamar Friedman, CEO of CodiumAI, currently approaches the problem while code is being written. His company has an AI bot that works as a pair programmer alongside developers, prompting them with tests that fail, pointing out edge cases, and generally poking holes in their code as they write, aiming to ensure that the finished product is as bug free as possible. He says a lot of tools for measuring code quality focus on aspects like performance, readability, and avoiding repetition. 

Codium works on tools that allow for testing of the underlying logic, what Friedman sees as a narrower definition of functional code quality. With that approach, he believes automated improvement of code is now possible, and will soon be fairly ubiquitous. “If you’re able to verify code logic, then probably you can also help, for example, with automation of pull requests and verifying that these are done according to best practices.”

Itamar, who has contributed to AutoGPT and has given talks with its creator, sees a future in which humans guide AI, and vice versa.  “A machine would go over your  entire repository and tell you all of the best (and so-so) practices that it identified. Then a few tech leads can go over this and say, oh my gosh, this is how we wanted to do it, or didn’t want to do it. This is our best practice for testing, this is our best practice for calling APIs, this is how we like to do the queuing, this is how we like to do caching, etc. It’ll be configurable. Like the rules will actually be a mix of AI suggestion and human definition that will then be used by an AI bot to assist developers. That’s the amazing thing.”

How is Stack Overflow experimenting with GenAI? 

As our CEO recently announced, Stack Overflow now has an internal team dedicated to exploring how AI, both the latest wave of generative AI and the field more broadly,  can improve our platforms and products. We’re aiming to build in public so we can bring feedback into our process. In the spirit, we shared an experiment that helped users to craft a good title for their question. The goal here is to make life easier for both the question asker and the reviewers, encouraging everyone to participate in the exchange of knowledge that happens on our public site.

It’s easy to imagine a more iterative process that would tap in the power of multi-step prompting and chain of thought reasoning, techniques that research has shown can vastly improve the quality and accuracy of an LLM’s output.

An AI system might review a question, suggest tweaks to the title for legibility, and offer ideas for how to better format code in the body of the question, plus a few extra tags at the end to improve categorization. Another system, the reviewer, would take a look at the updated question and assign it a score. If it passes a certain threshold, it can be returned to the user for review. If it doesn’t, the system takes another pass, improving on its earlier suggestions and then resubmitting its output for approval.

We are lucky to be able to work with colleagues at Prosus, many of whom have decades of experience in the field of machine learning. I chatted recently with Zulkuf Genc, Head of Data Science at Prosus AI. He has focused on Natural Language Processing (NLP) in the past, co-developing an LLM-based model to analyze financial sentiment, FinBert, that remains one of the most popular models at HuggingFace in its category. 

“I had tried using autonomous agents in the past for my academic research, but they never worked very well, and had to be guided by more rules based heuristics, so not truly autonomous,” he told me in an interview this month. The latest LLMs have changed all that. We are at the point now, he explained, where you can ask agents to perform autonomously and get good results, especially if the task is specified well. “In the case of Stack Overflow, there is an excellent guide to what quality output should look like, because there are clear definitions of what makes a good question or answer.”

What about you? 

Developers are right to wonder, and worry, about the impact this kind of automation will have on the industry. For now, however, these tools augment and enhance existing skills, but fall far short of replacing actual humans. It appears some of bots have already learned to automate themselves into a loop and out of a job. Tireless agents that are always working to keep your code clean. I guess we’re lucky that so far they seem to be as easily distracted by time consuming detours as the average human developer? 

Technology marches on, but procrastination remains unbeaten. 

We are compiling the results from our Developer Survey and have tons of fascinating data to share on how developers view these tools and the degree to which they are already adopting them into their workflows.

If you’ve been playing around with ideas like this, from self-healing code to Roboblogs, leave us a comment and we’ll try and work your experience into our next post. And if you want to learn more about what Stack Overflow is doing with AI, check out some of the experiments we’ve shared on Meta.

The post Self-healing code is the future of software development appeared first on Stack Overflow Blog.

We sit down with Forrest Brazeal, head of developer media at Google Cloud, to discuss all the AI-powered goodies announced at today’s I/O event. Plus, a conversation with Paige Bailey, lead product manager for generative models at Google, who contributed to many of the projects that debuted today.

Learn more about Forrest on his website and check out his newsletter.

You can follow Paige on Twitter or her LinkedIn.

Get on the list to try out some of the new stuff released today here.

TRANSCRIPT

The post A conversation with the folks building Google’s AI models and I/O releases (Ep. 569) appeared first on Stack Overflow Blog.

[Note to readers: before leaving a comment about someone with no skills wasting your time, refer back to the title and remember that you can’t insult a person who has already completed a perfect self-own.]

Anyway, over the last month, I decided to try diving back in, inspired by a steady stream of posts I saw on social media that showed people writing natural language instructions that today’s AI assistants can transform into working code. Maybe, I thought, my basic understanding of how a web app gets built will allow me to engineer the right prompts, and the AI can handle writing and debugging the actual code. 

The app I had in mind is fairly simple: people can list let others know when they are going to be at the local dog park. After some discussion, I found that this is a basic CRUD app:

• Create: a web form where users can input the name of their dog and the time they plan to arrive at the park. 

• Read: Other users can see who is planning to visit and what time they’ll be there. 

• Update: I’m not even trying to get this fancy! Also, no take-backsies!

• Delete: At the end of each day, the database deletes all entries so the slate is blank for the following morning. 

Normally, to get started, I would brush up on my paltry HTML skills and prepare a sacrifice to the JavaScript gods, but,  in 2023, I can just ask an AI: 

I want to build a single page web app that will allow users to submit their name, their dog's name, and the time they intend to visit the local dog park. After users submit this information, it is displayed for anyone who visits the page. I need front end code and a database on the backend that can store state. 

First - Please explain how you would create this app using pseudo-code examples. 
Second - write the code for this app and share it as a single code snippet.

First, let me outline the general structure and pseudo-code for the app.
Frontend (HTML, CSS, JavaScript)
a. Create an HTML form for user input (user's name, dog's name, and intended visit time)
b. Style the form using CSS
c. Add JavaScript to handle form submission and send data to the backend API
Backend (Node.js with Express and a database like MongoDB)
a. Set up a Node.js server with Express
b. Create API endpoints to handle data submission and retrieval
c. Connect to a MongoDB database to store and fetch the submitted data
Connect frontend and backend
a. Use JavaScript to send data from the frontend to the backend API
b. Display the fetched data on the frontend

Ok, let’s drop the code it generated into my WordPress CMS just to take a peek and…by George, it works.

<!-- index.html -->
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Dog Park App</title>
    <style>
        /* Add your CSS styles here */
    </style>
</head>
<body>
    <h1>Dog Park App</h1>
    <form id="dog-park-form">
        <input type="text" id="userName" placeholder="Your name" required>
        <input type="text" id="dogName" placeholder="Dog's name" required>
        <input type="time" id="visitTime" required>
        <button type="submit">Submit</button>
    </form>
    <ul id="visitors-list"></ul>
    <script>
        // Add your JavaScript code here
    </script>
</body>
</html>

Looks a little janky, though. Let’s clean things up. 

Edit the code above so that the three text fields are centered on the page and there are three line breaks between the name and time fields. 

And just like that, the changes are made. I’ll spare you that code snippet as it’s largely the same.
Looks better, but it’s still missing something. I know! 

Modify the code above so that an ASCII image of a dog appears over the text fields for name and time. The ASCII image of the dog is centered on the page.

<!DOCTYPE html>
<html>
<head>
	<title>My Webpage</title>
	<script>
		// This function clears the text area every 24 hours at midnight
		function clearText() {
			var currentTime = new Date();
			var hours = currentTime.getHours();
			var minutes = currentTime.getMinutes();
			var seconds = currentTime.getSeconds();
			if (hours == 0 && minutes == 0 && seconds == 0) {
				document.getElementById("output").value = "";
			}
		}
	</script>
	<style>
		/* This style centers the text fields and the dog image on the page */
		.container {
			display: flex;
			flex-direction: column;
			align-items: center;
		}
		input[type="text"], textarea {
			display: block;
			margin: 0 auto;
		}
		.ascii-dog {
			font-size: 50px;
			text-align: center;
			margin-bottom: 50px;
		}
	</style>
</head>
<body onload="setInterval('clearText()', 1000);">
	<div class="s-code-block container">
		<div class="s-code-block ascii-dog">
			<pre>
  __      _
o'')}____//
 \"''''''''\\
   \        \
    )________\
    |_|_|_|_|_|    
			</pre>
		</div>
		<label for="name">Name:</label><br>
		<input type="text" id="name"><br><br><br>
		<label for="time">Time:</label><br>
		<input type="text" id="time"><br><br><br>
		<button onclick="displayText()">Submit</button><br>
		<label for="output">Output:</label><br>
		<textarea id="output" rows="5" cols="50" readonly></textarea>
	</div>
	<script>
		// This function displays the text from the input fields in the output area
		function displayText() {
			var name = document.getElementById("name").value;
			var time = document.getElementById("time").value;
			var output = document.getElementById("output");
			output.value += name + " - " + time + "\n";
		}
	</script>
</body>
</html>

How sweet it is. This is what  mean when they say AI is a tool to unlock human creativity and potential, not to replace us.

So far so good, but the input doesn’t persist. I need some kind of backend to record my state. 

I want to add a database to the code above so that I can store the state of the output and display all text submitted to users on the client side. I want the database to contain two rows, one for "name" and one for "time". When users submit a "name" and "time" the database stores this state and it's displayed in the output section. The database clears these rows once a day at midnight Eastern time. 

A few seconds later the AI spits back a code block that uses jQuery and PHP with a MySQL database. For a hopeless programmer like me, it’s fascinating to see that I’ve now got access to building blocks in multiple languages. I can’t even master one on my own!

That said, the AI can’t solve the issue of ME being an intractable vortex of bugs and errors, attracting obstacles to functioning code like a magnet picks up nails. I go through the process of setting up an AWS account and following the online tutorial for creating a MySQL database, but can’t actually get it to connect to the workbench. 

The AI tries to be kind. I ask it to rewrite the code for a NoSQL database and it helpfully switches from PHP to Node.JS without missing a beat. I spin up a MongoDB Atlas cluster, but am lost again in a sea of error messages. 

Eventually I try a clean slate. I start a new dialog with the AI and ask it to create a simple app that will work with Firebase. I’ve learned a few things from my first two attempts, so I understand a little better how the pieces are supposed to fit together. It’s easier for me to work in the terminal and to have a clean file and folder structure. At 9:30pm on a random Tuesday, I’ve got a functioning CRUD app—input your info about your next visit to the dog park, refresh the page and there it is for the world to see. 

You can accuse me of talking my book, but in all honesty, there were some things the AI simply couldn’t solve for. It insisted I needed the code below:

​​<!-- The core Firebase JS SDK is always required and must be listed first -->
  <script src=“https://www.gstatic.com/firebasejs/9.6.8/firebase-app.js”></script>
  <!-- Add Firestore (database) -->
  <script src=“https://www.gstatic.com/firebasejs/9.6.8/firebase-firestore.js”></script>

But it didn’t connect that to an error I kept getting:

Uncaught SyntaxError: Unexpected token 'export'

A quick web search and I found the following question and answer pair. Do I understand why deleting that code fixed the issue? Of course not. But it let me get closer to a working solution. (Ed. note – removing this code fixed the error, but caused an issue with the window refreshing when a user clicked the submit button. I later added it back in, and got refresh working, and didn’t encounter the error a second time.)

The AI also had a bunch of ideas about how to solve for this one:

Uncaught SyntaxError: Cannot use import statement outside a module

I tried three or four of its solutions, but we got nowhere. But the web had what I needed. I fed the context of the answer back in and voila, a working web app.

Index.html:

<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8">
  <meta name="viewport" content="width=device-width, initial-scale=1.0">
  <title>Palatine Bark Play Scheduler</title>
  <style>
    * {
      box-sizing: border-box;
    }
    .banner {
      background-color: #4CAF50;
      color: white;
      text-align: center;
      padding: 1rem;
      margin-bottom: 1rem;
    }
    .container {
      display: flex;
      justify-content: space-around;
      flex-wrap: wrap;
    }
    form {
      display: flex;
      flex-direction: column;
      align-items: center;
      padding: 1rem;
      width: 50%;
    }
    .data-section {
      width: 50%;
      display: flex;
      flex-direction: column;
      align-items: center;
    }
    .data-container {
      width: 100%;
      padding: 1rem;
      text-align: center;
    }
    img {
      max-width: 100%;
      height: auto;
      margin: 2rem 0;
    }
    /* Media query for smaller screens */
    @media screen and (max-width: 767px) {
      form, .data-section {
        width: 100%;
      }
    }
  </style>
</head>
<body>
  <div class="s-code-block banner">
    <h1>Palatine Bark Play Scheduler</h1>
  </div>
  
  <div class="s-code-block container">
    <form id="data-form">
      <label for="name">Your Name:</label>
      <input type="text" id="name" required>
      
      <label for="dog-name">Your Dog's Name:</label>
      <input type="text" id="dog-name" required>
      
      <label for="time">Time:</label>
      <input type="time" id="time" required>
      
      <button type="submit">Submit</button>
      <img src="https://firebasestorage.googleapis.com/v0/b/palatine-bark.appspot.com/o/good%20boy.png?alt=media&token=XXXXXXXX" alt="Good Boi" />
    </form>
    <div class="s-code-block data-section">
      <h2>Today's Data</h2>
      <div class="s-code-block data-container">
        <div id="data-display"></div>
      </div>
    </div>
  </div>
<!-- Firebase App (the core Firebase SDK) -->
<script src="https://www.gstatic.com/firebasejs/9.6.8/firebase-app-compat.js"></script>
<!-- Firebase Firestore -->
<script src="https://www.gstatic.com/firebasejs/9.6.8/firebase-firestore-compat.js"></script>
<!-- Your custom JavaScript file -->
<script type="module" src="app.js"></script>
</body>
</html>

App.js:

// Initialize Firebase
const firebaseConfig = {
  apiKey: "MYAPIKey",
  authDomain: "coolest-dogpark-scheduler.firebase.com",
  projectId: "Bens Awesome Project Goes Here",
  storageBucket: "Ben's Bucket",
  messagingSenderId: "NUMBERS",
  appId: "LOTTA CHARACTERS"
};

// Initialize Firestore (Database)
const app = firebase.initializeApp(firebaseConfig);
const db = firebase.firestore(app);

// Form and data display
const form = document.getElementById('data-form');
const dataDisplay = document.getElementById('data-display');

// Handle form submission
form.addEventListener('submit', async (event) => {
  event.preventDefault();
  
  const name = document.getElementById('name').value;
  const dogName = document.getElementById('dog-name').value;
  const time = document.getElementById('time').value;
  const timestamp = firebase.firestore.Timestamp.now();
  
  await db.collection('data').add({ name, dogName, time, timestamp });

  // Clear form
  form.reset();
  location.reload();
});

// Fetch data and display
async function fetchData() {
  const today = new Date();
  today.setHours(0, 0, 0, 0);

  const querySnapshot = await db.collection('data')
    .where('timestamp', '>=', firebase.firestore.Timestamp.fromDate(today))
    .get();

  dataDisplay.innerHTML = '';

  querySnapshot.forEach(doc => {
    const data = doc.data();
    dataDisplay.innerHTML += `<p>${data.name} - ${data.dogName} - ${data.time}</p>`;
  });
}

// Call fetchData() initially and whenever the form is submitted
fetchData();
form.addEventListener('submit', fetchData);

Lots of folks are making claims about AI replacing programmers, but for the time being, the effect on my usage was the opposite. The AI was the inspiration to try coding again; it was a springboard that got me going and handled some basics. But it wasn’t enough to get me to the finish line on its own. When things started to get tricky, I was pinging colleagues in chat for help, or searching up error messages and sifting through answers from Stack Overflow, technical documentation, and blog tutorials.

What do you call something that can string together complex concepts and provide useful answers to questions about everything from history to poetry to programming? A friend of mine suggested “thought calculator” and I’ve fallen in love with this phrase. It perfectly captures this new technology’s power, and its limitations. 

The AI isn’t sentient or autonomous, as far as we know, but it has a form of intelligence which you can leverage as a tool. Coding is one of its best applications, because it uses textual instructions to produce an objective output. We can argue forever about the quality of an AI’s marketing copy or literary essay, but with programming, setting aside for a moment the important question of code quality, we can test to see if it produces the desired result. 

As our CEO announced last week, we’re thinking about ways we can use the power of generative AI to continue building a knowledge community that is open and accessible to all. Some folks protested that it would be wrong for us to train AI on Stack Overflow data, but the reality is lots of people are already doing that. We could sit around and do nothing while other organizations ingest the web into an algorithmic black box, or we could try to build a system where human input is still recognized and rewarded, where the output created by the collaboration of a human and their thought calculator is something everyone can then leverage and learn from. 

We are all in the process of figuring out how to use these new tools in a safe and ethical manner. We would love to hear from the community about how you’re approaching the issue. If you’ve been experimenting with AI to help you write code, let us know what you think in the comments. I’ll try to be back in a week or two with an update, once my army of autonomous agents completes my plan for world domination.

The post The worst coder in the world tries an AI sidekick appeared first on Stack Overflow Blog.

Dean Tribble, CEO of Agoric, joins Ben and Ryan to talk about his journey from working on early programming languages at Xerox PARC to leading a company developing an open-source blockchain.

Episode Notes

Smart contracts aren’t actually new. Computer scientist, legal scholar, and cryptographer Nick Szabo coined the term in 1994 (possibly earlier, depending on who you ask). 

Old problems seem to keep coming back. Bret Victor gave a talk in 2013 called “The Future of Programming,” where he talked about problems from 1973 that were still relevant. 

To learn more about the Agoric blockchain, check out their homepage. 

If you’d rather shape how the blockchain itself operates, much of Agoric’s code is open source. 

Connect with Dean on Twitter or Telegram

TRANSCRIPT

The post From Smalltalk to smart contracts, reflecting on 50 years of programming (Ep. 556) appeared first on Stack Overflow Blog.

A Principal Engineer at GitHub, Kris is president of the Nivenly Foundation and an admin at Hachyderm, an instance of the decentralized social network powered by Mastodon. 

The ongoing changes at Twitter have fueled interest in alternative, decentralized platforms like Mastodon and Discord.

Read Leaving the Basement, Kris’s post about scaling and migrating Hachyderm out of her basement.

Watch Kris’s conversation with DigitalOcean Chief Product Officer Gabe Monroy about building decentralized IT platforms.

Find Kris on Twitter, GitHub, Twitch, or YouTube.

Congrats to Lifeboat badge winner metakeule for answering: How can I get an error message in a string in Go?

TRANSCRIPT

The post How to keep the servers running when your Mastodon goes viral (Ep. 555) appeared first on Stack Overflow Blog.

This week we sit down with some fellow Stackers, Erin Yepis and Joy Cicman Liuzzo, to discuss the results of our latest Pulse Survey. Developers told us what emergent technology they expect to become mainstream, what they think is a fad that will pass, and how they feel about everything from AI to open source to blockchain.

Episode Notes

You can dive deeper into the research, including some lovely matrix charts, on our blog.

Erin has also explored tag trends among our most loved languages and job insights from our community.

Learn more about Joy on her LinkedIn.

Thanks to our Lifeboat badge winner of the week, russbishop, for helping to answer the question: Where is the app content folder in the simulator of Xcode?

TRANSCRIPT

The post Developers think AI assistants will be everywhere, but aren’t sure how to feel about it (Ep. 548) appeared first on Stack Overflow Blog.

During my three years working on the Stack Overflow podcast and blog, I’ve gotten the chance to talk with lots of interesting folks working with a wealth of microservices and containers. I’ve seen the push to build infrastructure as code and the appeal of going serverless. At the same time, I’ve chatted with lots of folks in the areas of observability and service meshes, who have found a new business supporting the sprawl of interconnections that exists in modern applications.

Recently, however, I’ve noticed a new trend growing in parallel. Yes, adoption of public cloud continues to grow, with many companies still in the process of deciding what to migrate off local servers. Tons of folks gathereveryday to share knowledge about AWS, Azure, and Google Cloud across our Stack Overflow Collectives.

At the same time, however, a growing number of organizations are also carving out space to repatriate work from public providers to on-prem private clouds and, for the growing world of edge computing and machine learning, going back to the future of actually owning and operating their physical hardware on-site. 

A cloud to call your own

According to a 2022 report by Bessemer Ventures, there has been a significant uptick in the adoption of virtual private clouds. The report suggests that, “it is becoming easier to package SaaS products and deploy them inside a customer’s virtual private cloud (VPC). This is due in part to the standardization around Kubernetes as the operating system of the cloud. This makes it easier for SaaS companies to serve a wider range of customers that may prefer to keep certain sensitive data or applications in a VPC.” 

A lot of our customers using Stack Overflow for Teams Enterprise edition opt for this approach. We build and upgrade the platform for knowledge sharing and collaboration, but it’s installed in a private or on-prem location and the conversations about their proprietary code clients are discussing stay privates on-prem.

Tom Limoncelli, a technical product manager on our site reliability team, has strong opinions on this trend. “Here’s what’s really happening,” he wrote to me: 

a. Running your own datacenter encourages bad practices due to lack of governance and other reasons.

b. The cloud forces/encourages better practices, such as strict governance, infrastructure as code, and fully automated CD/CD pipelines.

c. People are building on-prem clouds, which emulate those best practices because they got a taste of in the cloud.

Another way to say that is… People aren’t returning to the datacenter; they’re returning to on-prem clouds because datacenters can be frustrating.

The way Limoncelli sees it, a fully DIY approach encourages bad practices. Owners tend to treat servers more like pets than cattle, adding their own customization. After decades of that, you get a datacenter that is just one big mess of bad configuration ideas, mismatched technologies, and political barriers that prevent any of that from being fixed. The smart way to move to private cloud is to be strict about standardization. In other words, no, you can’t request a special machine with a weird ethernet connection because one person thinks it’s cool.

Cloud systems, on the other hand, provide an API to request new virtual machines in minutes, instead of a manual purchase process that took months. They install racks and racks of the same hardware configuration. They use standardized machine configs, guiding users away from bespoke configs. Costs are accounted for, which often doesn’t happen in datacenters. On the software side, the move to the cloud is an opportunity to adopt automation like a CI/CD pipeline, weaning people off of manual deployments.

Users acquire resources via an API, not by a purchase order. Governance and automation are established from the start. The combination of accessing resources by a standardized API and automatically enforced governance results in a system that is more maintainable and enforces more modern practices. 

Containers will set you free

As Nick Chase argues over at The New Stack, Kubernetes has been a powerful enabler for companies looking to gain more control over their usage of the cloud. It’s relatively agnostic about the real or virtual hardware you choose to employ because it can do a wealth of different things with the Linux kernel as its foundation. 

Kubernetes was designed to make it simpler for a small group of people to manage a large constellation of applications by abstracting the underlying hardware. Barring a setup that confines your system to a scarce resource, it offers a level of resilience that customers ten years ago turned to public cloud providers for. Along with allowing users to update systems without going offline, it also offers capabilities for monitoring of services up and downstream, something that many microservice heavy organizations are now turning to third-party observability providers for.

“Kubernetes’ superpowers change the game in important ways,” writes Chase. “If you can deploy, scale and manage the lifecycle of Kubernetes, you can use it to pave over public and private cloud infrastructures, optimize costs and overheads aggressively, and treat everything underneath Kubernetes as a commodity.”

As my colleague Ryan Donovan pointed out during a recent conversation, “being able to abstract infrastructure has enabled a lot of cloud providers, but it’s also allowed folks to have those containers located anywhere — within a public cloud, on a prem server in Lithuania, or a private cloud replicated across multiple locations.” Just because your infrastructure has moved to the cloud doesn’t mean you don’t care about proximity to users and the advantages that might provide you in terms of cost or latency.

Stack Overflow has taken advantage of some of these superpowers. Max Horstmann, formerly a Staff Software Engineer at Stack Overflow, now a principal software engineer on the Azure Kubernetes Service (AKS), wrote in depth about why Kubernetes might be a good choice and how we took advantage of it inside our organization. You read his article on it or listen to his podcast below. 

“If you’re starting a new project from scratch — a new app, service, or website — your main concern usually isn’t how to operate it at web scale with high availability,” writes Horstmann. “Hence, when it comes to choosing the right set of technologies, Kubernetes — commonly associated with large, distributed systems — might not be on your radar right now. After all, it comes with a significant amount of overhead.”

Despite all this, he sees value in adopting it from the start. “When you’re launching something new, your focus is typically to move fast and iterate quickly based on early feedback. Scaling is something for later. K8S is a tool that, in my view, allows you to do just that because it can accelerate your build/test/deploy loop, allows you to easily deploy and instrument different instances of your app, e.g. for split testing, customer demos etc.”

If you’re lucky enough to find product market fit and start to see a surge in customer demand, Kubernetes proves valuable in this area as well. “The problems that come with scale — fault tolerance, load balancing, traffic shaping — are already handled,” says Horstmann. “At no point will you hit that moment of being overwhelmed with success; you future-proofed your app without too much extra effort.” 

This comment from a HashiCorp’s forum sums up the advantages well: “A Kubernetes cluster is a good example of an abstraction over compute resources: there are many hosted and self-managed implementations of it on different platforms, all of which offer a common API and common set of capabilities.”

A bridge between public and private clouds

The Bessemer report cites another emerging technology trend that pairs increased cloud adoption with on-prem data. “Emerging middleware platforms are making it easier to bring the power of the cloud to the data, wherever it may be. This has played out in industries like financial services, where a wave of modern fintech infrastructure helped build bridges between the cloud and legacy banking systems. We are seeing similar bridges being built in other large industries like supply chain, logistics, and healthcare to bring the power of the cloud to these on-premise data sources.”

It’s important to define what we mean by “middleware” here. As Red Hat points out, the term dates back to a 1968 NATO conference on software engineering, where it referred to code that sat between the assembler/compiler at the bottom of the pyramid and the application logic at the top. In the world of hybrid cloud, middleware refers to an evolved version of this same idea. As Asanka Abeysiinghe, Chief Tech Evangelist at WSO2 explains in a blog, this can look like, “mega clouds that provide infrastructure as a service (IaaS)-enabled middleware capabilities via APIs, which have become the new DLLs. So, for example, message queues, storage and security policies are open for developers to consume in applications running on the IaaS (Infrastructure-as-a-Service).”

Outside the big public cloud providers, Abeysinghe sees other alternatives catching on. “Kubernetes addresses the issue of cloud lock-in by bringing an open standard to the cloud-native world, and it enables basic middleware capabilities as components. In addition, the Cloud Native Computing Foundation (CNCF) brings a rich set of Kubernetes-centric middleware, and you can find them in the CNCF technology landscape. However, if the middleware capabilities provided by Kubernetes and the CNCF are not enough for your application development, you can add custom resources by defining them in a custom resource definition (CRD) because Kubernetes is built using open standards.”

When I spoke with Abeysinghe for this article, he was quick to point out that there was no data to indicate a trend of companies moving fully away from the cloud, far from it. There are still more folks migrating onto the public cloud than off it. He estimates that 80 percent of activity is still focused on the traditional shift from local to public cloud, with another 20 percent moving in the opposite direction. But that 20 percent is important, precisely because it flows against the prevailing tide we’ve seen over the last decade. 

Abeysinghe believes that there is a realization, especially at organizations with a lot of legacy hardware infrastructure, that they now have a lot of machinery sitting idle. If you’re a big bank with decades of mainframes at your disposal, utilizing only five percent of that doesn’t make much sense. “Kubernetes lets you run a private cloud that better utilizes your existing on-prem hardware.” Cloud bursting technology lets you shift to third party resources when your local hardware is maxing out. 

Not to be left out of the game, public cloud providers now offer physical server racks to clients who have jobs that are more efficient on-prem, or need to remain in-house for security and compliance reasons. Companies that once helped to migrate companies off local hardware now offer server-racks-as-a-service bundled with your public cloud offering, a truly full circle moment for the evolution of compute.

Bringing AI models in-house

One area where this trend seems particularly strong is among companies focused on artificial intelligence that work with large data sets and have created their own models. “Big cloud GPU compute is very expensive, whether it’s for training or for inference,” says Dylan Fox, founder and CEO at Assembly AI, a startup that provides AI-as-a-service to companies that are seeking natural language capabilities in their offerings but don’t want to build the models or hire a team in-house.

“We do most of our training in on-prem instances. We have a couple hundred A100 NVIDIA cards, and we recently just purchased like a couple hundred more that we have for on-prem instances used to train.” The crypto winter has been a blessing for this market, as a glut of GPUs has come onto the secondary market and prices for new and used hardware have fallen.

As David Linthcium wrote over at InfoWorld: 

Companies are looking at other, more cost-effective options, including managed service providers and co-location providers (colos), or even moving those systems to the old server room down the hall. This last group is returning to “owned platforms” largely for two reasons.

First, the cost of traditional compute and storage equipment has fallen a great deal in the past five years or so. If you’ve never used anything but cloud-based systems, let me explain. We used to go into rooms called datacenters where we could physically touch our computing equipment — equipment that we had to purchase outright before we could use it. I’m only half kidding.

When it comes down to renting versus buying, many are finding that traditional approaches, including the burden of maintaining your own hardware and software, are actually much cheaper than the ever-increasing cloud bills.

Second, many are experiencing some latency with cloud. The slowdowns happen because most enterprises consume cloud-based systems over the open internet, and the multi-tenancy model means that you’re sharing processors and storage systems with many others at the same time. Occasional latency can translate into many thousands of dollars of lost revenue a year, depending on what you’re doing with your specific cloud-based AI/ML system in the cloud.

It’s not just small AI startups that want to crunch a lot of data at a low latency with homegrown models. Here’s an eye-opening quote from Protocol. “The on-prem trend is growing among big box and grocery retailers that need to feed product, distribution, and store-specific data into large machine learning models for inventory predictions, said Vijay Raghavendra, chief technology officer at SymphonyAI, which works with grocery chain Albertsons.” 

Raghavendra left Walmart in 2020 after seven years with the company in senior engineering and merchant technology roles. “This happened after my time at Walmart. They went from having everything on-prem, to everything in the cloud when I was there. And now I think there’s more of an equilibrium where they are now investing again in their hybrid infrastructure — on-prem infrastructure combined with the cloud,” Raghavendra told Protocol. “If you have the capability, it may make sense to stand up your own [co-location data center] and run those workloads in your own colo, because the costs of running it in the cloud does get quite expensive at certain scale.”

Chick-fil-A had a similar experience. In a blog written by Brian Chambers, the company’s head of Enterprise Architecture, he noted that, “In researching tools and components for the platform, we quickly discovered existing offerings were targeted towards cloud or data center deployments. Components were not designed to operate in resource constrained environments, without dependable internet connections, or to scale to thousands of active Kubernetes clusters. Even commercial tools that worked at scale did not have licensing models that worked beyond a few hundred clusters. As a result, we decided to build and host many of the components ourselves.”

Their solution allowed a DevOps Team and Smart Device Support to deploy, build, and update to thousands of restaurants. 

Cloud, with control

Total spending on cloud computing is already enormous and still projected to grow over 20% this year, closing in on a half a trillion dollars. But it will be a far more varied and nuanced period of growth. “Cloud is the powerhouse that drives today’s digital organizations,” said Sid Nag, research vice president at Gartner. “CIOs are beyond the era of irrational exuberance of procuring cloud services and are being thoughtful in their choice of public cloud providers to drive specific, desired business and technology outcomes in their digital transformation journey.”

After a decade or more spent moving away from server racks, companies are finding there can be advantages to running local infrastructure for certain kinds of compute. There is also, perhaps, a generational shift at work. The engineers who cut their teeth building big public clouds inside large tech companies see now moving on to create startups or take senior roles at smaller companies that specialize in a subset of cloud offerings. What’s old is new again, but with a vast variety of new flavors and permutations to choose from. 

The post Are clouds having their on-prem moment? appeared first on Stack Overflow Blog.

John Abel, Technical Director of Google Cloud’s Office of the CTO (OCTO), joins the home team to discuss what a typical day looks like for him. We discuss what he learns from his customers and why his enterprise customers are prioritizing developer experience through platform engineering and managed services in 2023. Plus: The BBC’s surprising history in computing.

Show Less

Episode Notes

John spent 25 years at Oracle before joining Google Cloud’s Office of the CTO (OCTO), a team that’s been called the company’s “secret weapon” in collaborating with major customers to solve their tech problems and drive long-term deals.

For more on his approach to tech and business, you can read this article he wrote on the seven points of driving lasting innovation

Learn more about OCTO from Business Insider.

Settle down for a good read: the full story of how the BBC’s microcomputer changed history.

Connect with John on LinkedIn or Twitter.

Today’s  Lifeboat badge winner is vscjones for their answer to:

How can I find the number of business days in the current month with JavaScript?

TRANSCRIPT

The post Why developer experience is the key to better software, straight from the OCTO’s mouth (Ep. 534) appeared first on Stack Overflow Blog.

Cassidy and Ceora are joined by Ben Holmes and Nate Moore, developers on the core Astro platform, to talk about the new features they’re working on, what they love about docs, and the role of open source in their work.

Episode notes:

Astro is a site builder that lets you use the frontend tools you already love (React, Vue, Svelte, and more) to build content-rich, performant websites.

Astro extracts your UI into smaller, isolated components (“islands”) and replaces unused JavaScript with lightweight HTML for faster loads and time-to-interactive (TTI).

Ben and Nate explain why Astro’s compiler was written in Go (“seemed like fun”).

To learn more about Astro, start with their docs or see what people are doing with the framework.

Connect with Ben on LinkedIn, GitHub, or via his website.

Connect with Nate on GitHub.

Shoutout to Lifeboat badge winner Aurand for their answer to How to convert list to queue to achieve FIFO.

TRANSCRIPT

The post The less JavaScript, the better (Ep. 532) appeared first on Stack Overflow Blog.

The team talks about voice-to-code features, how game developers built accessibility into God of War, and why lab-grown meat is officially safe to eat (hail seitan!). Plus: this YouTube channel is a strong contender for the most entertaining robotics content on the internet. 

Episode notes:

In a win for accessibility, GitHub Copilot now responds to voice commands, allowing developers to code using their voices.

Speaking of accessibility, learn how Santa Monica Studio worked with disabled gamers and the community to build accessibility into God of War Ragnarök.

The US Food and Drug Administration (FDA) has determined that lab-grown meat is safe to eat.

Looking for some high-quality entertainment content? Look no further than Simone Giertz’s YouTube channel, where she builds robots to (among other things) wash her hair and wake her up with a slap in the face.

Blast from the past: Listen to our episode with MongoDB CTO Eliot Horowitz.

Shoutout to Lifeboat badge winner ralf htp for their answer to How to listen for and react to Ace Editor change events.

TRANSCRIPT

The post From your lips to AI’s ears (Ep. 530) appeared first on Stack Overflow Blog.

On today’s episode we chat with Prof. Gregory Kapfhammer, Associate Professor in the Department of Computer Science at Allegheny College, and a specialist in the subject of flaky tests. He breaks down his definition of what makes a test flaky, how you can solve for it, and automated solutions that take some of the guesswork and busywork out of avoiding them altogether.

Episode Notes

There is a ton of great research to be found on Prof. Kapfhammer’s website, including: 

• Flaky Tests: Finding and fixing unpredictable and harmful test cases
• Database Testing: Automatically testing relational database schemas
• Web Testing: Detecting and repairing poor responsive web page layout

We’ve written a bit about how Stack Overflow is upping its unit testing game and how you can evaluate multiple assertions in a single test.

Thanks to our lifeboat badge winner of the week, Survivor, for answering the question: Is it possible to find out if a value exists twice in an arraylist?

And thanks to Andre for writing in to let us know that yes, there are folks who code on mobile. He suggests trying:
– Termux https://wiki.termux.com/wiki/Main_Page can be used as a
  terminal emulator. I have all I need here: Vim, git, node.js, Python
– Markor https://gsantner.net/project/markor.html has a HTML view

TRANSCRIPT

The post Flake it till you make it: how to detect and deal with flaky tests (Ep. 528) appeared first on Stack Overflow Blog.

The team talks to Matt Arbesfeld, cofounder and CEO of LogRocket, about the most challenging problems he’s solved for customers, how machine learning is shaping the next generation of LogRocket solutions, and why side projects that teach you how to experiment and make mistakes are just as (or even more) important than formal CS curricula.

LogRocket helps software teams create better experiences through a combination of session replay, error tracking, and product analytics.

LogRocket’s machine-learning layer, Galileo, cuts through the noise generated by conventional error monitoring and analytics tools to identify critical issues affecting users.

LogRocket is hiring, so check out their open roles or connect with Matt Arbesfeld on LinkedIn. You can also give LogRocket a free trial.

Are you looking for demos and innovative use cases on how to build smarter and more reliable automations with built-in connectors, low-code, integrated AI, and more? Explore the UiPath Dev Dive Series here.

TRANSCRIPT

The post From CS side project to the C-suite (Ep. 525) appeared first on Stack Overflow Blog.

The home team reflects on the last year, talks through tech news, and recommends some good reads for 2023.

Episode notes:

Adobe closed out 2022 and celebrated 40 years with an employee-only Katy Perry concert. Related: Ceora makes the case for virtual concerts.

DeepMind is teaching AI to play soccer, which naturally makes us think of QWOP.

ICYMI: Ghost calls out Substack and Substack responds.

BeReal is the iPhone app of the year. But not even Resident Youth Ceora knows anyone who actually uses it.

Some 2023 recommendations from the team: 

Ceora recommends Realworld (not to be confused with BeReal), an app that guides you through tasks and decisions big and small, from deciding on health insurance to improving your credit.

Cassidy recommends Bird by Bird: Some Instructions on Writing and Life, by Anne Lamott.

Matt suggests fellow side hustlers check out The Freelance Manifesto: A Field Guide for the Modern Motion Designer by School of Motion founder Joey Korenman.

Ben recommends Tomorrow, Tomorrow, and Tomorrow, a terrific novel about a love triangle between indie video game creators, especially fun if you grew up with Oregon Trail, Myst, and Super Mario. 

TRANSCRIPT

The post Our favorite apps, books, and games of 2023 (Ep. 524) appeared first on Stack Overflow Blog.

Welcome to a new year. For our first episode back, we’re featuring a chat with Jessica Hicklin, the CTO of Unlocked Labs. She describes what it was like to enter prison with a life sentence at the age of 16, how she taught herself to code in while incarcerated, and how she turned that into a new role as a software engineer and entrepreneur after being unexpectedly released at the age of 42.

Show Less

Episode Notes

If you want to read more about Jessica, you can check out the blog we worked on together for the launch of our Overflow Offline initiative. If you’ve ever wondered what it’s like learning to code from an XML file of raw Stack Overflow data, be sure to check this episode out.

You can learn more about the Supreme Court case that led to Jessica’s release here.

Her company’s mission is to build a better justice system from the inside, specifically by educating incarcerated individuals so they can teach the next generation and have valuable skills upon release. Read more about Unlocked Labs here.

Our lifeboat badge of the week goes to mx0 for answering the question: How do you extract the ‘src’ attribute from an ‘img’ tag using Beautiful Soup?

Follow Ben on Twitter and if you enjoy the show, be sure to leave us a rating and review.

TRANSCRIPT

The post From life without parole to startup CTO (Ep. 522) appeared first on Stack Overflow Blog.

I

I was born in Manhattan and lived much of my life in the Big Apple. I went to school on the Bowery and worked in office complexes that sat adjacent to storied destinations like Wall Street, Times Square, and Madison Square Park. I met sources for lunch and attended concerts and conferences that moved my career forward. But like many knowledge workers, in the wake of the pandemic, I’ve moved away from the concrete jungle and relocated to a small, rural town a few hours north of NYC.

I’m not alone. Recent data indicates that only 8% of office employees who worked in NYC pre-pandemic are back to the office five days a week. This creates a financial crisis for major urban areas. Fully 25% of NYC’s tax base each year has historically been derived from commercial real estate, anchored by offices in Wall Street and Midtown and the plethora of restaurants and stores and sidewalk vendors that cater to the millions of people who used to flow every day to and from the city’s commercial corridors. Big cities, in other words, aren’t what they used to be. But that leaves open a door to what cities might become.

New York City’s mayor, Eric Adams, addressed the need for change in a recent speech. “It’s imperative that our economic leaders sit down and say what our business centers and districts are going to look like,” Adams said. “Do we change the zoning? Do we allow these new workforce housing that’s coming together outside, because there’s new ways people are doing business?” 

There is something revolutionary in there. Working every day in the world of software developers and knowledge management, I think we’re at a tipping point that will change not just where we work—home or office—and how we work—remote, async—but the nature of our cities, our towns, and with them, our civilization. From London to São Paulo, from Boston to Berlin, there is an opportunity for the metropolis to emerge as something different, something equally essential, but perhaps more equitable, affordable, and humane. To get this transformation right, we can learn from the world of open-source software. 

II

What drove us to work in offices in the first place? For most of its history, the physical workplace served essential, utilitarian functions. DJ Huppatz and Agustin Chevez explain that “the office” began as a place where peace and solitude would allow for concentration and where important and rare works on paper could be safely stored: 

“The origins of the modern office lie with large-scale organizations such as governments, trading companies and religious orders that required written records or documentation. Medieval monks, for example, worked in quiet spaces designed specifically for sedentary activities such as copying and studying manuscripts. As depicted in Botticelli’s St Augustine in His Cell, these early ‘workstations’ comprised a desk, chair and storage shelves.”

Technology played a pivotal role in the development of the office. Computers once required entire floors—hell, entire buildings—to house their processing power. They shrunk over time, but offices still provided a venue for workers to access hardware that was unaffordable or impractical for use at home. Huppatz and Chevez point to 1964, when IBM introduced a magnetic-card recording device into a Selectric typewriter, as a tipping point. From there, the functionality and convenience of a small army of devices—copy machines, fax machines, server racks—gave employees good reasons to work from an office.

Even when code could be written at home on a PC, working from home as a programmer wasn’t necessarily practical. When I spoke with Paul Ford and Sara Chipps about their early careers in the 1990s, they recalled sitting in an office where versions of a software project were passed around on a physical disk. Essential backups of key files and data? Sometimes it was a few hard drives in a briefcase that you carried home at night. 

As a journalist, I worked for many years in fancy offices that served an essential function: a hub for physical work—collaborating on a newspaper or magazine printed on ACTUAL paper—and a place to access a company-owned PC where my work lived on local storage that wasn’t backed up to any cloud.

By 2015, however, I was acutely aware of the many hours a day I spent commuting and how unnecessary the commute was to completing my work—how, in fact, it often made completing my work harder. By that time, my work happened almost entirely in chat, emails, and online documents. Most desks still had a landline, but they sat unused, a relic of a different era of newsroom. 

I felt at the time that seeing people in person, especially my bosses, was key to advancing my career. I was told explicitly by my manager that I was expected at the office at least three days a week. Yet there were many days when I would arrive at the office and hear no chatter around the coffee machine, see no inspiring collaboration happening around a drawing board. Each worker, even in an open office plan without cubicles, was living completely in their own world: headphones on, multiple tabs open to Google Docs, Slack, Email, Spotify, Twitter, YouTube, and a dozen others. We sat or stood, our attention fixed on the screen, office banter happening in private messages and across Twitter canoes, not in the break room. 

For software developers, the advances of the last decade, especially the advent of cloud computing and version control, meant that asynchronous contribution to a code base was just as practical from home as the office. Pre-pandemic, however, the majority of large tech companies invested heavily in real estate and dictated that employees spend at least several days a week in the office. The transformative shock of our recent quarantines and the rapidly growing success of companies founded around open-source projects, however, is finally catalyzing a change away from this archaic approach.

III 

The pandemic exposed an unspoken truth. People were not less productive working from home; in fact, many got more work done. What gives? Well, subtract an hour of commute each way. Subtract another hour spent walking to grab coffee, snacks, and lunch. Remove an hour here or there for all the collaboration that happened around the ping pong table or Xbox. Take out the stand-ups, check-ins, and meetings spent on chit-chat and vague ideas which, ya know, could have been an email.

Why did so many companies, including supposedly forward-thinking tech companies, insist on a heavy investment in office and real estate even as most office work moved to portable devices tied to the cloud? And why are so many of the most valuable tech companies in the world still battling to get workers back into the office now? 

As Huppatz and Chevez write, the office acts as a “visible statement of prestige and power.” Companies that have invested heavily in fancy office parks want them bustling with employee activity when clients, partners, or journalists come to visit. Another imperative for management, usually left unsaid, is that the office allows them to implement monitoring, surveillance, and control. The pair write:

Various management theories also had a profound impact on the office. As Gideon Haigh put it in The Office: A Hardworking History, the office was “an activity long before it was a place”.

Work was shaped by social and cultural expectations even before the modern office existed. Monasteries, for example, introduced timekeeping that imposed strict discipline on monks’ daily routines.

Later, modern theorists understood the office as a factory-like environment. Inspired by Frank Gilbreth’s time-motion studies of bricklayers and Fredrick Taylor’s Principles of Scientific Management, William Henry Leffingwell’s 1917 book, Scientific Office Management, depicted work as a series of tasks that could be rationalized, standardized and scientifically calculated into an efficient production regime. Even his concessions to the office environment, such as flowers, were intended to increase productivity.

For obvious reasons, physical products in development and proprietary technology need to be safeguarded. Work on these projects might require an office or workspace separate from the home. But the vast majority of code can now be written safely and securely from home. The tension between employees and organizations boils down to management’s fear that over time remote workers will be less productive and predictable. Given what we’ve seen during the pandemic, however, the onus is on leaders to show that working from home is less productive before insisting that working from an office is somehow superior.

Think about the value created by products like Linux and Python, Bitcoin and Ethereum, GoLang and React. Sure, people sat in rooms over the years and worked together to drive these projects forward. But it wasn’t the frisson of IRL interactions that turned them into the global juggernauts they are today. Quite the opposite: it was the ease with which anyone around the world could contribute to the project without needing any special permission. 

Tech companies have become the most valuable organizations on earth, and the folks who write code at these companies command, on average, the highest salaries of any profession. I won’t try and predict what the future will hold, but I think it’s safe to say that coders are capable of building incredibly impactful and profitable tools, platforms, and business models without leaving the comfort of their pajamas. Increasingly, workers in finance, entertainment, education, and other industries are finding ways to do the same.

We have an opportunity for a radical rethinking of the office—and the city beyond. 

IV

Before we go on, I want to offer an aside to make one thing clear. I’m not denigrating work that doesn’t involve code or that can’t be done remotely. The pandemic reminded us of another important truth—that our society can’t function without farmers and doctors, truckers and teachers. While a lot of ink has been spilled on the future of work, the majority of Americans, and most people around the world, can’t actually do their jobs remotely. This being Stack Overflow, however, where we serve a community of developers and technologists, it makes sense to focus on the option of remote work and what the expansion of that kind of work might mean for our society. I’ll also acknowledge that I’m an American and the perspective here is centered on the US. To the degree that it’s similar or different from the experience in other locales, I would love to hear from readers with more knowledge and experience than me.

So, back to the issue at hand. The question we should be exploring is not how we can force people back into offices to save the old model of a city, but what cities can become now that so many workers who once had to congregate there to make an impact have the option to work remotely. What would a reimagined urban center look like for these professions? 

We know, from decades of research, that urbanization tends to exacerbate income inequality. In countries like the United States, a decades-long trend also saw manufacturing move away from smaller cities towards international hubs, leaving hundreds of mid-sized cities and their surrounding suburbs struggling with urban blight and rising poverty, which grew fastest in suburban areas during the period following the Financial Crisis of 2008. 

For areas outside the biggest metropolitan areas, hybrid work has been a huge boon. Take Troy, NY, a city of 50,000 close to my new home in the Hudson Valley. As The Globe and Mail reported: 

For years, these small legacy cities – gutted by a loss in manufacturing, pockmarked by abandoned industrial spaces, and hampered by a dwindling population – have struggled to make a sustained economic recovery. Yet the tides may finally be shifting. The rapid expansion of hybrid and remote workplaces during the pandemic, along with a climate crisis that has underscored the vulnerability of our bigger cities and laid bare the necessity for community resilience, has suddenly made places like Troy ripe for adaptation in the 21st century.

The well-established concept of “rewilding” urges societies to return lands back to their natural state, rebalancing environments where plants and animals were shunted aside in favor of human civilization. Hybrid and remote work provide us an opportunity for a re-widening, a dispersal of human capital that unwinds some of the concentration to urban areas we’ve seen over the last century, restoring a better balance.

Imagine a world in which massive office districts of major cities are remade to attract residents with remote or hybrid jobs who choose their home based not on its proximity to their corporate office, but what it offers in terms of great schools, hospitals, arts, entertainment, parks, waterfront, and community. Giant office buildings could offer flexible work space that can be rented short- or long-term by individuals or organizations.

Converting office districts to live-work zones would offer a much needed influx of new residential space, helping to combat the rising cost of homes and rentals. Citizens who do work essential to the livelihood of a community, such as teachers, healthcare providers, and service workers are provided with tax breaks, as needed, to ensure they can afford to live alongside those whose work can be done fully remotely.

Knowledge workers like me, who move out of the city, make urban spaces more affordable for essential workers who staff hospitals and restaurants. Meanwhile, small towns and cities that were hollowed out by deindustrialization over the last 30 years get an influx of new residents to support their tax base. Again, the majority of jobs don’t allow for remote work, but a great deal of wealth is concentrated among the jobs that do. Empowering or even encouraging those workers to live wherever they want could have a positive impact on the affordability of cities and the economic health of rural communities.

Forward-thinking cities can still focus on attracting top-tier workers in areas like finance, technology, and law, but they will do so by making themselves wonderful places to work, live, and play, not by insisting on the primacy of an antiquated 9-to-5 office culture.

The lesson I take from the open-source revolution and the last two decades of software development is that the platforms and tools with the least friction tend to win out. A “butts-in-seats” mentality that demands a regular commute on a rigid schedule creates a ton of unnecessary friction—in our jobs and in our lives. The city of the future, I hope, will be a place where anyone can safely and securely contribute their ideas or apply their skills. Make the permissionless innovation of open source the bedrock ideology of the next generation of urban centers, and we can start to build a new metropolis better-suited to our post-industrial age of information.

The post Remote work is killing big offices. Cities must change to survive appeared first on Stack Overflow Blog.

On today’s episode we chat with Anthony Dellavecchia, a developer advocate at Twilio, about some of his favorite tools for boosting productivity and why he went all out building his personal website.

Episode Notes

You can learn more about Anthony here.

His favorite terminal tool at the moment is Warp, which describes itself as “a blazingly fast, Rust-based terminal reimagined from the ground up to work like a modern app.” 

His personal website features a live chat function. Sometimes it’s actually Tony, sometimes it’s just a bot. 

No lifeboat badge today. We”ll be taking a break for the holidays and will resume episodes in 2023. Until then, enjoy the holidays. 

TRANSCRIPT

The post Let’s talk about our favorite terminal tools (Ep. 521) appeared first on Stack Overflow Blog.

We sit down for a chat with Steve Sewell, CEO at Builder.io, to talk about the experiences that inspired him to craft a visual CMS and start a company around it. Along with coding and running a company, Steve has become a popular content creator, and he explains why he believes short form TikToks are a great format for teaching people to program.

Episode Notes

Steve was working as an engineering manager at ShopStyle and found that an increasing amount of his team’s time was spent working on custom requests from departments like marketing and sales. They tried headless CMS but the data and components couldn’t keep up with ever evolving needs. They wanted a drag and drop system connected to their code, data, and components.

This pain point inspired him strike out on his own to create a new product. The vision was a tool that would allow colleagues from across a company to make changes to web pages without requesting dev time, but would also ensure that any changes made would be up to the standards of the design department and not introduce errors that engineering would then have to fix. 

Hence, the company’s pitch for a plug & play system that integrates with your existing sites & apps. It relies on a few key ideas:

• API-based infrastructure that is native to your tech stack
• Works with any frontend or backend
• Build with your own data, like product catalogs or customer data platforms, to create rich, dynamic experiences

You can check it out for yourself over at Builder.io.

Follow Steve on Twitter and TikTok where he breaks down websites and effects he finds interesting.

Congrats to phoenisx for being awarded the Necromaner badge after answering the question: Property ‘share’ does not exist on type ‘Navigator”? 

The post Chatting about drag and drop tech stacks with Builder.io’s Steve Sewell (Ep. 519) appeared first on Stack Overflow Blog.

On today’s episode, we’re airing a conversation recorded at the Next.JS conference. We chat with Lee Robinson, VP of Developer Experience at Vercel about the company’s vision for evolving from Webpack to Turbopack, helping customers who are cautious about migrating to a new tool, changes happening with React server components, and much more.

EPISODE NOTES

Webpack has been king for several years. Vercel wants folks to embrace Turbopack, but their claims about speed raised a lot of backlash after it was first announced. Lee explains why he thinks the Rust-based approach will ultimately be a big benefit to developers and how organizations who are deeply ingrained with existing tools can safely and incrementally migrate to what is, for now, a very Alpha and experimental release. 

We go over the routing and rendering updates in Next.JS 13, exploring where it might offer developers more flexibility and the ability to use React server components to ship less, maybe a lot less, JavaScript. As Lee says in the episode: 

“So to your point about wanting to ship less JavaScript, that was a kinda fundamental architectural decision of where we headed with the app directory. And the core of this is because it’s built on React server components. 

The key thing with React server components is that as your application grows in size from one component to a hundred thousand components, the amount of client-side JavaScript you send can be exactly the same. It can be constant because you can render every single component on the server. 

And that’s a lot different from the world of React applications today, where every new component you add for data fetching or just putting some HTML on the screen also adds additional client-side JavaScript.

So this is kind of inverting the default, back from the client to be server first. Now, of course, we still love client-side interactivity that React provides making really interactive and rich UI experiences, but the default for data fetching or just getting HTML to the browser happens from the server, and that’s gonna help us reduce the amount of JavaScript.”

You can learn more about Lee on his website, LinkedIn, and Twitter. To diver deeper into his take on how Rust will impact the future of Javascript, check out a post he wrote here.

TRANSCRIPT

The post Ready to optimize your JavaScript with Rust? (Ep. 517) appeared first on Stack Overflow Blog.

On today’s episode we chat with Andrew McFarlane, CTO at Validation Cloud. His company focuses on building out infrastructure for blockchains, supporting the nodes and validators that keep everything running and verified. McFarlane explains where popular languages like Rust and Go can be found in the Web3 world and why he thinks a crypto winter is the best time to be building fundamental tech.

Episode Notes

You can learn more about Andrew, from building out a telco in Canada to cyber security at Deloitte, on his LinkedIn.

Validation Cloud bills itself as the world’s fastest node infrastructure and cites networks like Bitcoin, Ethereum, and Binance as clients it supports. Learn more at the company’s website here.

The company announced the launch of it’s latest product, Javelin, earlier today.

Shout out to this week’s lifeboat badge winner, Derek, for helping answer the question: How do you open  the file chooser in an Android app using Kotlin?

TRANSCRIPT

The post The blockchain tech to build in a crypto winter (Ep. 516) appeared first on Stack Overflow Blog.

On today’s episode, Matt and Ben talk about data showing Silicon Valley losing its status as tech’s center of gravity. Plus, what it means to make major engineering changes in public and how to reckon with the collapse of some of the biggest names in crypto.

Episode Notes

Data show’s Silicon Valley’s share of new startup funding deals dropped below 20% for the first time.

What does it mean to experiment with big changes to an engineering org, in public and in real time?

SBF would like the chance to explain himself.

Today’s lifeboat badge goes to CodeCaster for explaining: What is E in floating point?

TRANSCRIPT

The post Taking stock of crypto’s crash (Ep. 515) appeared first on Stack Overflow Blog.

In today’s podcast episode, Ben, Matt, and Cassidy talk with Utkarsh Srivastava, VP of Engineering at Patreon. We cover the product roadmap, deployment best practices, and UX philosophies. Matt and Cassidy, both Patreon users, confirm its delightful user experience.

Episode notes:

Srivastava reflects on his upbringing in India, learning to write Assembly, and going to Stanford University to complete his Ph.D in computer science.

He shares his early career experiences at big tech names like Yahoo!, Google, Twitter, and Google.

The group reflects on some of the engineering challenges at Patreon including technical debt, migrations to open source services, and troubleshooting bugs.

Srivastava walks us all through upcoming product features that his engineering team is working to implement.

Andy wins a Lifeboat Badge for answering this question about a list of all tags on Stack Overflow.

Follow Ben, Matt, Cassidy, and Utkarsh.

TRANSCRIPT

The post From Twitter Bootstrap to VP of Engineering at Patreon, a chat with Utkarsh Srivastava (Ep. 514) appeared first on Stack Overflow Blog.

On this episode, we chat with Max Howell, creator of Homebrew, about his new package manager, Tea, and how it aims to solve the problem of providing funding for popular open source projects.

Notes 

Over the years Homebrew, an open source package manager, has emerged as the project with the greatest number of individual contributors. Despite all that, it’s creator Max Howell, couldn’t make a living off the occasional charity of the millions of people who used the software he built. The XKCD cartoon below is probably the most frequently repeated joke on the podcast over the last three years.

While he is not a crypto bull, Max was inspired with a solution for the open source funding dilemma  by his efforts to buy and sell an NFT. A contract written in code and shared in public enforced a rule sending a portion of his proceeds to the digital objects original creator. What if the same funding mechanism could be applied to open source projects? 

In March of 2022, Max and his co-founder launched Tea, a sort of spirtual successor to Homebrew. It has a lot of new features Max wanted in a package manager, plus a blockchain based approach to ensuring that creators, maintainers, and contributors of open source software can all get paid for their efforts. 

You can read Max’s launch post on Tea here and yes, of course there is a white paper.

TRANSCRIPT

The post The creator of Homebrew has a plan to get open source contributors paid (Ep. 511) appeared first on Stack Overflow Blog.

Phillip Shoemaker thinks we’re at a critical turning point for the web, with identity and privacy being core, foundational priorities. Imagine an internet where it’s easy to provide just the data you want or need to exchange. Envision being able to protect your anonymity, no questions asked.

Shoemaker isn’t exactly new to the topic of turning points for the web. He grew up in Cupertino, around the corner from Apple headquarters. His dad was an engineer at IBM. He eventually ended up working for Apple in 2009 where he helped the company navigate one of the biggest turning points in internet history — the launch of the App Store

In today’s podcast episode, we reflect on Shoemaker’s career experiences and discuss why he’s now focused on decentralized networks of trust.

Episode notes:

Shoemaker spent his childhood in Silicon Valley and learned Assembly when he was just 16 years old.

In his early 20s, he applied to work at Apple and was continually rejected. So he went to work for seven startups instead.

Finally, in 2009, Shoemaker ended up at Apple overseeing the review process for the App Store.

After seven years at Apple, Phillip became interested in cryptocurrency after discovering his personal information on the dark web.

His interest grew in the topic of self sovereign identities, which led him to become CEO and co-founder of Identity.com.

Phillip and Ben reflect on the utility of Web3 in gaming.

Follow Ben and Phillip.

Thank you to lifeboat badge winner Marchingband for their answer to the question about running C or C++ code from Node.js in an efficient way.

TRANSCRIPT

The post Fighting to balance identity and anonymity on the web(3) (Ep. 507) appeared first on Stack Overflow Blog.

At some point, a lot of developers think about becoming entrepreneurs. Some end up taking the jump. So what happens when it turns out that nobody wants your product?

Cara Borenstein, co-founder at Stashpad, ended up in this exact situation. After a two year stint as a software engineer at Twilio, she saw an opportunity to create a notepad for developers to stay on top of context switching and manage knowledge-related tasks. V. 1 was a wiki that didn’t quite catch on.

Embracing this reality, Borenstein and her team decided to dig deeper by talking with target customers. That process catalyzed a transformation of the core product into something people need and love, a second brain for busy developers that helps them stay focused and retain those stray thoughts that can add up to something big later on.

In today’s podcast, Matt, Ceora, and Cassidy reflect on Cara’s founder journey.

Episode Notes:

Cara shares her experiences living in New York and San Francisco— and why she and her co-founder ultimately located Stashpad in North Carolina.

She elaborates on the exact steps that she took to pivot her startup following limited initial interest in V1 of the product.

Despite being in the Bay Area and working at Twilio, she was struggling to meet people because her full brain power was going to her products.

She shares what it was like for her and her co-founder to hire Stashpad’s first employees.

The group discusses Stashpad’s pathway to monetization in the context of developers wanting free tools.

Follow, Ceora, Matt, Cassidy, and Cara.

Marchingband gets today’s lifeboat badge for their answer to the question about running C or C++ code from Node.js in an efficient way. 

The post Going from engineer to entrepreneur takes more than just good code (Ep. 506) appeared first on Stack Overflow Blog.

Being a technologist is more than a 9-5 job. It’s a lifestyle. That’s why so many of us, like the mad scientists we are, get into homelabbing.

What does this hobby/obsession entail? Build a home lab to help you level-up your tinkering game. Think: media servers, Raspberry Pis, data centers—turning your home into an IT paradise guaranteed to make you more productive, if only it wasn’t so enticing to work on.

Today’s podcast episode is all about brainstorming fun ideas for homelabbing. Matt, Ceora, and Cassidy host a discussion with JJ Asghar, Developer Advocate at IBM.

Episode notes:

The group laughs about setting up JIRA workflows and Trello boards for our family lives—Matt says heck no.

Ceora speaks to the power of homelabbing as a way to gain profitable skills. 

JJ talks about the VPN system he has running on his phone to access his home network using tools like WireGuard and ZeroTier.

Cassidy suggests setting up a personal knowledge base as a second brain (and recommends Obsidian). 

JJ shares how homelabbing is popular among kids under 18 as a pathway for them to get into the tech industry.

Follow, Ceora, Matt, Cassidy, and JJ.

High fives to Lifeboat Badge winner Manquer for the answer to his question How can I upgrade the Yii 1.x version to the Yii 2.0 latest release version?

The post DIY mad science…it’s all about homelabbing (Ep. 504) appeared first on Stack Overflow Blog.

On today’s episode we chat about some of the fun announcements coming out of today’s Next.JS conference. Vercel announced it acquired Splitbee to bring first-party analytics to it’s platform. Next.JS 13 Introducing a redesigned approach to website layouts, data-fetching, and server-rendering. And last but not least, we were introduced to Turbopack, built by the creator of Webpack and Vercel. Turbopack is a Rust-based incremental bundler. Vercel claims that it shows updates 10x faster than Vite and 700x faster than Webpack. You can read more Turbopack here.

The post Goodbye Webpack, hello Turbopack! The big news from today’s Next.JS conference (Ep. 502) appeared first on Stack Overflow Blog.

Human beings are easily excitable creatures. We pump ourselves full of sugar, and then we crash. The cycle repeats. Now, here we are at a unique moment in Internet consciousness where we’ve experienced multiple crypto winters in addition to the phenomenon known as Dogecoin. Satoshi, wherever he may be, must be #facepalm to the moon. So should we take this stuff seriously—especially those of us who quit our jobs for crypto vaporware?

On today’s podcast, we have an open source OG sharing his voice of reason—to show us what’s real in an avalanche of digital nonsense. John deVadoss spent 18 years as a general manager at Microsoft where he helped build .NET and VSCode, among other things, during the early evolution of what are now widely adopted, even pivotal pieces of technology .

So what brought him to blockchain land?

Episode notes:

John explains that Web3 is about the convergence of technology, economics, and social trends.

He elaborates that foundations begin with service-based architecture (SOA), the notion of how to design loosely coupled systems that consist of economic services and components.

He goes on to explain how DeFi represents this thinking of a loose composition of services.

With all of this, blockchain brings together technology and economic incentives into a holistic equation—people contribute because they want to contribute.

Nonsense it is not, says baby Yoda.

Crypto isn’t the end game. It’s a segue along the way.

Follow Ben, Matt, and John.

Learn more about the Global Blockchain Business Council and John’s company, ngEnterprise.

Speaking of awesomeness, we’d like to give a shout out to Stellar Question Badge winner GateKiller for asking a question “How can I get the DateTime for the start of the week?” that has been bookmarked by a hundred people.

TRANSCRIPT

The post He helped build .NET and VS Code — Now’s he working on Web3 (Ep. 500) appeared first on Stack Overflow Blog.

Many coders would say they rely on Stack Overflow to get work done, but Hicklin’s situation is different. She had no access to the internet while incarcerated. “My experience with the internet ended with America Online and dial-up modems.” At first she relied on textbooks, but they were often out of date. Eventually, a friend who worked in tech sent her an XML file containing Stack Overflow’s quarterly data dump. With that raw material, Hicklin and her co-founder built out a curriculum and learning management system that is now utilized by individuals studying through Unlocked Labs. 

Today, we’re happy to announce a new initiative called Overflow Offline. We’re working with a non-profit, Kiwix, to ensure that an up-to-date version of our dataset is easily available for those who need it, and will work to improve its readability and reduce its size so there is less friction for end users. Unlocked Labs is one of the organizations we’ll be working with, but there are many others, spanning from the justice system, to scientific research, to university education in areas where internet access is scarce. 

We first set out to create this project in the fall of 2019. We had heard that there were communities that would benefit from an offline version of Stack Overflow and wanted to understand what it would take to create. What we learned was that Kiwix had already done great work on this, and had been distributing Stack Overflow to many users. In fact, it was the second most popular data set in their entire library, behind only Wikipedia. 

Since 2018, however, Kiwix was unable to update its offline version of Stack Overflow. Over the last two years, we were able to provide them with financial and technical support to unblock the issues preventing these updates, and to provide resources for improving the usability of the data on their platform. 

“Over the years demand for Stack Overflow’s dataset has only continued to grow. With their help we are now able to offer this resource again, and have seen it widely adopted by those coding in situations where there is little to no internet access,” says Stéphane Coillet-Matillon, co-founder of Kiwix. “We built the Sotoki (Stack Overflow to Kiwix) scraper in such a way that it can capture each and every one of the 180 Stack Exchange websites.”

The pandemic prevented us from moving ahead with new deployments, as in-person activity was limited, but we have now reached a point where the work we’ve done with Kiwix can be released to the world and hopefully continue to be improved as an open-source project.  

The Users

Along with Unlocked Labs, groups like The Last Mile, Bard Prison Initiative, and Code 4000 have also found that the questions and answers our community has generated, now over 20 million and counting, can be an invaluable resource. 

“When you have a problem you cannot simply go to the internet and search for help,” says Neil Barnby, an instructional officer with Code4000. “This is huge disadvantage for the Code4000 students, but Stack Overflow offline allows them to search the resource for possible solutions. This means they become more independent in finding their own solution and gets them familiar with the resources they will eventually use when they are released. It also means that they can work more efficiently on the commercial work they undertake to develop their portfolios.”

In the world of science, Stack Overflow is used offline in locations like The IceCube Lab, a remote research station at the South Pole that studies the universe by observing neutrinos.   

“We constantly work on scripts, a lot of Python code, for instance. We use Puppet down there. So every time we need to make a major change on the cluster, there’s always something that doesn’t work. That’s when Stack Overflow comes in handy,” says Ralf Auer, the IceCube Data Center Manager. 

There are two people onsite year-round to keep the experiments running and there are hundreds of scientists around the world that depend on the data the lab produces. Keeping all the tech running is tough when internet access is spotty to non-existent. “Right now we update once a year during the summer season when I can go down there with a drive. There is no way for us to download 135 gigabytes over the satellite,” says Auer. “Of course it would be nice to get updates more frequently than what we have right now. When I look there and I have a problem with Python, the knowledge on Stack Overflow is just incredible. Just the amount of knowledge that is already out there is very handy for us.”

A third use case for Overflow Offline is for students studying at schools where internet access isn’t consistent, or for those who might not have internet access to help with homework when they are done with class. “Cameroon has a population of 27 million. The Internet coverage rate in Cameroon is 34%, or 9.15 million people have access to the Internet,” says Yannick Nkengne, an ed-tech entrepreneur and founder of the company EduAirBox. “In the education sector, offering free Wi-Fi on university campuses in Cameroon is expensive for administrations. Almost no campuses in Cameroon have free Wi-Fi for students.  Students pay for internet packages via their smartphones to connect to their laptops and the price of effective packages for research is expensive for the majority of students. With our solution, students can download content from the EduAirBox to read at home off our network. Their browser uses Web Storage (IndexedDB) technology to store data.”

As a former computer science student, Nkengne is familiar with Stack Overflow. “The fact that Kiwix is able to distribute the Stack Overflow platform was good news for my team because 30% of students in Cameroon are in digital courses and this rate is growing. We are planning to install Stack Overflow in all the networks of our universities. By the end of this year, about 50,000 students will be able to access Stack Overflow without an internet connection.”

The Future

Stack Overflow sees today’s launch as the jumping off point for Overflow Offline. As we learn from our partners and users, we’ll endeavor to improve the dataset so that it’s accessible to more organizations and provides a more powerful resource to those learning to code or building with software.
If you want to learn more about how you can support Kiwix and their millions of users without reliable internet access, check out their site here. If you’re interested in contributing to their open source project, check out their list of onboarding tickets here, or jump straight to the Sotoki repository on Github.

The post Introducing the Overflow Offline project appeared first on Stack Overflow Blog.

Our CEO, Prashanth Chandrasekar, kicked things off with a discussion on the state of work and the factors that are key to a developer’s learning journey and success on the job. Drawing on data from our most recent developer survey, he laid out a positive vision for a future of hybrid work and online learning.

Next up was our CTO, Jody Bailey, chatting with Chris Kohr, a VP of Engineering at Salesforce. Nearly 70% of developers say they encounter a knowledge silo at least once a week, and 62% spend more than 30 minutes a day searching for answers or solutions to problems. For a team of 50 developers, the amount of time spent searching for critical information adds up to between 333-651 hours of time lost per week across the entire team.

The pair discussed strategies for helping developers avoid knowledge silos and context switching and explored some of the keys to getting into a flow state that maximizes both productivity and happiness. 

The final morning session was a fireside chat between our Chief Marketing Officer, Khalid El Khatib, and the journalist and author, Clive Thompson, whose book, Coders: The Making of a New Tribe and Remaking of the World, is a rich ethnographic study of the programmers who help craft our modern society. The pair had the audience in rapt attention with plenty of laughs as they explored what it takes to be a self-taught developer in today’s tech industry.

In the afternoon, Seth Hodgson, VP of Engineering at Udemy, talked about how to approach skills acquisition as a daily habit. As the demands of the workplace change and organizations shift to keep pace and continue to innovate, their workforce requires constant reskilling. In fact, 87% of leaders say they expect to face major skills gaps over the next five years. He discusses an approach that enables real-time, hands-on practice and peer-driven knowledge sharing, which has enabled Udemy’s 54M learners and 12.5K enterprise partners to always be at their best.

Next up, Stack Overflow CTO Jody Bailey held a fireside chat with Alex Bulat-van den Wildenberg, Group Technology Director and CTO at Capgemini, discussed how scaling subject matter experts and uncovering domain expertise can ultimately drive team and product growth.

After a short break, Stack Overflow Chief Product Officer Teresa Dietrich shared how Stack Overflow builds for the technologist’s holistic learning journey and what updates to expect across all of our products: Stack Overflow for Teams, Collectives, Employer Branding, and Advertising.

Following Teresa, Stack Overflow Chief Marketing Officer Khalid El Khatib spoke with Maggie Hulce, Executive VP, GM of Enterprise at Indeed, and Sally Bolig, Global Head of Employer Branding at Etsy about the ultra-competitive talent market today and the Great Resignation still reshaping our workplaces.  How do you attract talent, retain team members, and scale your expertise across your growing team? They discussed how this talent war stands independent from economic trends, the importance of understanding developer workflows in today’s talent climate, and how tools, onboarding, learning, and collaboration will all impact the talent market indefinitely.

Finally, Human-Computer Interaction researcher Dr. Gloria Mark delivered the closing keynote speech. While we’re unable to embed her talk, look for her new book Attention Span: Finding Focus and Fighting Distraction out in January 2023.

What comes next? 

This was our inaugural customer conference, and we had the privilege of getting to interact with employees who lead their internal communities on Stack Overflow for Teams. We were also thrilled that many members of our Stack Overflow community attended. We met folks who had started Stack Exchanges and other who had been asking and answering questions on our platform for over a decade. Given the success of this conference, you can look forward to future Flow State events next year.

The post Missed our Flow State conference? Catch up on all the sessions appeared first on Stack Overflow Blog.

Today’s streaming services have a vast content library, and a vastly different programming challenge than traditional television stations. Where linear TV tries to schedule content into time slots so the right demographics will see it and enjoy it, streaming services let you watch any content, any time you want. That means these service need to find a way to deliver the right content to every user, balancing what they will want with what will provide value over the long term. That’s where machine learning comes in.

On this sponsored episode of the podcast, Ben and Ryan talk with Shrikant Desai and Sowmya Subramanian, two engineering leaders at Warner Bros. Discovery who shape how their ML program figures out what your next favorite show might be. We cover the tools they’ve been using to build their learning pipelines, how a viewer’s history can shape their future, and whether ML algorithms can fill a human curator’s role to surprise and delight viewers.

Episode Notes

Our guests have done most of their ML work on AWS offerings, from AWS Personalize for their initial recommendation engine to SageMaker for model training and deployment pipeline. Now they’re building models from scratch in TensorFlow. 

Want to see these recommendations in action? Check out the offerings at Discovery+ and HBOMax. 

If you’re a ML/AL data scientist looking to shape the future of automated curation, check out their open roles. 

Follow our guests on LinkedIn:

• Shrikant Desai
• Sowmya Subramanian

TRANSCRIPT

The post Meet the AI helping you choose what to watch next (Ep. 494) appeared first on Stack Overflow Blog.

The best part about being tech builders is that we get to collaborate with some super-smart teammates. Every brain is unique, and we need this thought diversity to solve problems, build better products, and be more proud of our individual contributions as a result. But if you talk to a lot of people who self-identify as neurodiverse in tech, you’ll notice that folks tend to share the same experience of feeling a lot of pressure to fit in. 

In today’s podcast, Matt and Ceora talk with Wesley Faulkner, senior community manager at AWS Cloud, and Mariann Lowery, Product / UX Research Lead here at Stack Overflow about their experience as neurodivergent individuals and how we can all do a better job supporting our teammates while taking steps to feel more empowered in our own differences, too.

Episode notes:

Mariann shares how she and her UX research team at Stack Overflow are taking steps to create a more inclusive product experience, while reflecting on her experiences as a mother to a neurodiverse daughter.

Wesley talks about what it’s like to be a developer with dyslexia and why self-empathy and self-compassion have been important to his evolution as a senior leader.

Ceora explains why it’s important to be on a psychologically safe team from her perspective as a Black woman who is also neurodivergent.

We talk about giving people the space necessary to do their best work, implementing more inclusive hiring practices, and everyday routines that help us stay our happiest and most productive.

We conclude with a note about why supporting neurodiversity is good for everyone of all walks of life.

Follow Ceora, Wesley, and Mariann.

TRANSCRIPT

The post The many strengths of neurodivergence (Ep. 493) appeared first on Stack Overflow Blog.

In the world of technology, it feels like more and more software gets added to our workflows every day. Commit code, request a day off, expense home equipment, check your production code for errors—all these tasks use different tools. Sometimes it feels like all the software out there is just trying to steal our time. But is there some way that software can help optimize your time and let you get more things done?

On the fourth and final episode of our sponsored podcast series with Logitech, Ben and Cassidy talk with Paolo Passeri and Giulio Barresi about the ways that software can give us time back. 

Show notes:

Giulio gives building UI components as an example of where software innovation has given him time back: he started building them as static images in Photoshop, then Sketch brought connected, interactive components, and Finally, Figma let you collaborate and build an entire system together.  

If you missed any of the previous episodes, you can find them waiting for you here. 

Connect with Paolo Passeri on LinkedIn. 

Connect with Giulio Barresi on LinkedIn. 

Check out more mechanical keyboard products from Logitech. 

Congrats to KnutKnutsen for their answer to How can I specify a one-argument constructor using Lombok?, saving the question and picking up a Lifeboat badge.  

The post Don’t let software steal your time (Ep. 491) appeared first on Stack Overflow Blog.

When we recorded this podcast episode, we heard rumblings that the Ethereum merge was coming. Now it’s here, and we’re in watch-and-wait mode to see its impact. Meanwhile, it seems to be the best and worst of times in the world of chip manufacturing. NVIDIA and AMD are releasing a new line of GPUs while automobile manufacturers have no choice but to cut back on features. Now that mining crypto is dead, maybe we can finally upgrade our video card. Today’s podcast brings up a lot of questions about humanity and its devices. Ben and Matt reflect on the challenges of hybrid work for hardware developers, Apple Watch’s health features, and Ethereum’s promise for energy efficiency.

It finally happened. In the words of the Ethereum Foundation, ETH is now “ready for its interstellar voyage,” having transitioned from proof of work to proof of stake. With no centralized authority insisting on a ship date, we’re witnessing a feat. We’re all wondering what comes next. 

The Great Debate about hybrid and remote work continues. Is the decentralized talent movement winning? What can we do to prevent cabin fever? What do government workers do with their laptops if they need to cross the border?

The semiconductor chip shortage hasn’t ended yet, but some companies seem to be hurting more than others. What gives?

We conclude with a reflection on the new Apple Watch—and whether it can actually save our lives.

Be sure to follow @mattkander and @benpopper on Twitter to keep the convo going.

Big thanks to Androidian who is our latest Inquisitive badge recipient for coming to Stack Overflow for 30 separate days, maintaining a positive question record.

TRANSCRIPT

The post Ethereum finally merges, semiconductors stay scarce (Ep. 490) appeared first on Stack Overflow Blog.

On this sponsored episode of the podcast, we spoke with Martin Mao, CEO and co-founder of Chronosphere, about the increased difficulty in diagnosing errors in production, especially during a crisis. Complex systems create more data, and to paraphrase: more data, more problems. Chronosphere wants to do more than just give you observability into your problems; they want to help automate the response. 

Show notes

Like other folks we’ve talked to on the podcast, Chronosphere was born out of work pioneered at Uber. When you can’t find solutions to help you scale, sometimes you have to build them. 

Everything in Chronosphere was built from scratch, from the ingestion tier to the query layer. If you’re going to build something cloud native from the ground up, the clear choice for the team was Go. 

Cloud native observability changes the way developers interact with their code in production. Infrastructure is more complex, dev and test environments are gone, and data increases massively while data sources are more ephemeral. 

Congrats to david, who won a lifeboat badge for their answer to Can we convert a byte array into an InputStream in Java?

The post Five nines uptime without developer burnout (Ep. 488) appeared first on Stack Overflow Blog.

Developers and software companies are always chasing anything that will make them more productive: to shorten the distance between thinking of a solution and coding it down to near-zero. We’ve talked about the mindset and methods for getting into a flow state on a previous episode of this series, but what if part of unlocking that flow is just better integrating your hardware with your software?

In the third episode of a podcast series sponsored by Logitech, we explore developer productivity, flow state, and the impact hardware and software can have on these key aspects of a programmer’s workday. Our guests on this episode are Laurent Gillet, head of embedded software, and Tanvi Shah, head of software development. 

Episode Notes

We dive into some of the ways developers can customize their keyboard with shortcuts, macros, and apps to eliminate repetitive tasks and automate the busywork that stands in the way of bigger, breakthrough innovations. 

Flow state can be affected by things as simple as the right lighting, so Logitech created keyboards that automatically adjust their keyboard backlighting. 

For those not familiar with the MX series, you can read more about the different versions, including the mechanical one, here.

If you don’t know about Cassidy’s passion for keyboards, you can check out her website here or listen to a previous episode diving deep into the details of mechanical keyboards here.

If you missed episode two, you can check it out below. In it, we chat with Marcel Twohig, Head of Design for the MX Series at Logitech, and Thomas Fritz, Associate Professor of Human Aspects of Software Engineering at the University of Zurich. We cover the research that Professor Fritz has done on flow states, the design work that Marcel and team have done to incorporate that research, and the tools that you can use to maximize your daily flow.

The Stack Overflow blog is committed to publishing interesting articles by developers, for developers. From time to time that means working with companies that are also clients of Stack Overflow’s through our advertising, talent, or Teams business. When we publish contributionsfrom our customers, we’ll identify it as Partner Content with tags and by including this disclaimer at the bottom.

The post Can integrating hardware with software save developers time and energy? (Ep. 487) appeared first on Stack Overflow Blog.

On this sponsored episode of the podcast, we chat with two keyboard specialists from Logitech, Giulio Barresi, Lead UX Designer on the MX Series and Olivia Hildebrand, Global Product Manager on the MX Series. We brought along our own mechanical keyboard expert, Cassidy Williams, for a discussion about the impact a keyboard’s hardware, software, and design can make on developer productivity.

For those not familiar with the MX series, you can read more about the different versions, including the mechanical one, here.

If you don’t know about Cassidy’s passion for keyboards, you can check out her website here or listen to a previous episode diving deep into the details of mechanical keyboards here.

Stayed tuned for episode #2, airing next week, when we’ll be digging deeper into the science behind keyboards and coders with Prof. Thomas Fritz and Marcel Twohig Head of Design for the MX series.

TRANSCRIPT

The Stack Overflow blog is committed to publishing interesting articles by developers, for developers. From time to time that means working with companies that are also clients of Stack Overflow’s through our advertising, talent, or teams business. When we publish work from clients, we’ll identify it as Partner Content with tags and by including this disclaimer at the bottom.

The post Flow state at your fingertips: How keyboards impact developer productivity (Ep. 481) appeared first on Stack Overflow Blog.

Well, here’s a staggering statistic for you. According to Nick Bloom, a professor of economics at Stanford focused on researching the shift from working in offices to working at home, the trend towards WFH has started to stabilize. It was roughly 5% pre-pandemic, jumped to more than 60% during the height of lockdown, and has now leveled off at around 30%. There has been a six-fold increase, in other words, in people working from home between the start of 2020 and today.

In America alone, estimates Prof. Bloom, that translates to saving roughly 200 million hours and six billion miles EACH WEEK. Let that sink in for a second. If we extrapolate across the globe, there may be upwards of a BILLION hours previously spent on commuting that can now be devoted to learning, working, and recuperating for the next batch of productivity.

How are employers, organizations, and software developers responding to this tremendous change? That’s just one topic we’ll explore at Flow State on Wednesday, September 28. The event will gather developers, technologists, and technology leaders to discuss some of today’s biggest challenges and how to solve them.

For example, let’s say hybrid and remote work has cut way down on employees average time spent commuting each week, but also reduced the ease with which they can meet face to face or find a subject matter expert. 

Nearly 70% of developers say they encounter a knowledge silo at least once a week, and 63% spend more than 30 minutes a day searching for answers or solutions to problems. For a team of 50 developers, the amount of time spent searching for answers/solutions adds up to between 333-651 hours of time lost per week across the entire team. You’ve got all this time back if you skip the commute, but many teams no longer have the ability to shout across a room or walk down the hall to shoulder tap a subject matter expert. 

How do you empower a flow state over a state of disruption? Jody Bailey, Stack Overflow’s Chief Technology Officer, will discuss this issue with engineering leaders from companies like Salesforce and Walmart. We’re hosting multiple panels featuring technical leaders with deep experience in the software business who will discuss why redefining productivity means better defining the developer experience.

As the workplace evolves, so do the skills developers, managers, and executives need to thrive. Organizations are undergoing a massive shift as they look to keep pace with innovation while navigating vast time zone differences, increasingly asynchronous work and an ongoing battle for relevance which requires constant reskilling. In fact, 87% of leaders say they expect to face major skills gaps over the next five years with a heavy reliance on the developer community. We’ll be hearing from Udemy’s VP of Engineering, Seth Hodgson, who will discuss how developers can increase their operational effectiveness to drive better business outcomes by regularly addressing skills gaps in the flow of work.

There will be lots of other terrific talks at the event. Clive Thompson, who wrote the book Coders, will sit down with our own Khalid El Khatib, Stack Overflow’s Chief Marketing Officer for a fireside chat. You can also hear from Dr. Gloria Mark, Chancellor’s Professor of Informatics at the University of California, Irvine, a visiting senior researcher at Microsoft, and author of the forthcoming book Attention Span. She’s the researcher behind a staggering stat we cite often: We spend an average of just 47 seconds on any screen before shifting our attention. It takes 25 minutes to bring our attention back to a task after an interruption. 

The event is hybrid and every single talk will be broadcast to developers and technologists everywhere. (And if you need a sweetener beyond the great content, anyone who joins will get some Stack Overflow stickers in the mail!) We will gather a very limited number of technology leaders in New York to attend the conference live, where they can select their own Stack Overflow t-shirt with an exclusive design printed on-site and pick up an exclusive copy of Stack Overflow Magazine’s premier issue. If you’re based in New York and interested in attending live, click here. Due to capacity limitations, in-person attendance is limited. Again, all are welcome to attend virtually but you can apply to join us in New York by visiting flowstate.stackoverflow.co and clicking “Request to attend in-person”.

See you on September 28th!

The post Work has changed. Our upcoming conference, Flow State, explores what’s next appeared first on Stack Overflow Blog.

The home team talks students using AI pair programmers to complete their assignments, how the Godot game engine may be monetized through W4 Games, and whether paid tiers and subscriptions provide a healthy option for social networking apps.

Episode Notes

You can find a great essay on AI helping students, and what that means for their teachers, here.

Here’s a piece on W4 Games plans to monetize the Godot engine.

Snap says it now has one million subscribers for its Snapchat+ offering.

There were no fresh lifeboats badges this week, so shoutout to Jemo for being awarded the Great Question badge. They asked: What’s the difference between thread and coroutine in Kotlin

TRANSCRIPT

The post Does AI-assisted coding make it too easy for students to cheat on schoolwork? (Ep. 480) appeared first on Stack Overflow Blog.

Stack Overflow has been around for nearly 15 years and has become an ever-evolving encyclopedia of knowledge created and curated by a community of technologists. We’ve always been focused on helping technologists learn, and this year, for the first time, we’re launching a program to work with university students on campuses. 

Why are we launching this program? 

We want to learn how you engage with our site, get your input on what we can improve, and work out how to evolve Stack Overflow as a learning tool for the next generation of technologists. We will also offer the opportunity to pursue interesting challenges and earn rewards.

To help us with this effort, we’re recruiting our first cohort of Student Ambassadors. These ambassadors will represent us on campus, partner with us to bring more of their classmates on board, and take a leadership role in completing challenges, earning rewards, and helping us plan what future semesters will look like. For this semester, we’re partnering with Major League Hacking (MLH), which has a terrific track record of working with students from a wide range of schools. For now, we are working just with schools that have an MLH presence, but will be exploring options for how to expand in the future.

So, what do I need to do as a Student Ambassador?

The basic ask of you is simple. Sign up to be a Student Ambassador, create a Stack Overflow account (if you don’t already have one), and help us host some free pizza nights on campus where students will learn about our platform. Really, it is that simple.

These events will be part of the MLH Pizza Fund. You can use the pizza nights for study sessions, project work, or hackathons—it’s up to you. For every student you recruit to attend the event or sign up for our public platform, we’ll add on extra treats like soda and dessert.

Now, these pizza nights aren’t the only thing we’re doing this semester. If you want to go further, we’re partnering with MLH on three week-long hackathons. Teams that participate get to hear from our engineering staff and can earn rewards for completing various challenges. We’re planning to give away lots of t-shirts and stickers, and for those feeling lucky, raffle off the chance to win your own copy of The Key.

OK, so you can earn pizza and snacks, you can take part in challenges, and you can learn from our engineers. What else can Student Ambassadors do with us this semester? 

For teams that complete challenges during the hack weeks, we’ll shout you out on the Stack Overflow blog, podcast, and newsletter, which collectively reach over three million developers each month and will be featured for a day across every Stack Overflow Q&A page. If you can’t attend any of the three hack weeks but still want to take on a challenge, we’ll work with you to try and find a time for your team to participate this semester. 

Oh, and one last thing. Students who join us will get access to an instance of Stack Overflow for Teams. Think of it like your own private Stack Overflow, a place to ask questions about this program, learn more about MLH or upcoming hackathons, or simply share knowledge with other students. 

Thanks for taking the time to consider our Student Ambassador Program. For now, we’re working with schools that have an MLH presence on campus. If you have a campus club or are planning a hackathon that you think would be a good fit, please apply through the Student Ambassador website or email me directly (bpopper@stackoverflow.com) and we’ll get in touch to discuss what’s possible in future semesters. 

The post Stack Overflow is launching a Student Ambassador Program. Here’s how to apply. appeared first on Stack Overflow Blog.