Principles of Making

by Dineth Mendis

  • ,

    Thinking beyond your team

    Recently, couple of my teams decided to combine their codebases. It was essentially the same application, written twice over to do the UI for a wizard that went down 2 paths. Their backends do very different things. However, the customer sees a very similar interface. After having done the migration, there have been some gripes.…

  • , ,

    Do all software engineers care about customer impact?

    I got into a fun chat with my friends about unengaged people at work. Do software engineers care about salary, solving a problem technically (discovery), shipping, or does that work has to have impact in someone else’s life? Of course, different people find joy in many points within this spectrum of outcomes. Interesting question surfaced:…

  • Barry to Google on “increasingly aggressive Google”

    Worth the read (images in the post). Having been at Expedia, this issue is all too familiar. I hope someone does something.

    Google should profit share for the data they use to run their business, much like OpenAI should for its data for LLMs.

    Twitter link

  • ,

    Play the long game with people, the short game with outcomes

    Recently, @henry sent over my 2020 performance evaluation I had shared with him. I was just about to go from Principal to Director role. I’m still trying to get good at this. Such wonderful advice from @AC. Thanks boss! Play the long game with people, the short game with outcomes. Knowing how much to push,…

  • , ,

    Car crashes and sticking to your lane

    My team recently made the decision to not have QA role as part of experience engineering. There were a lot of complains on increased workload and not wanting to do testing, including some valid reasoning around testing not being an area of expertise. I’ve heard similar complaints when we spoke about creating dashboards and alerts…

  • Anticipatory Failure Determination

    [AFD] has the objective of identifying and mitigating failures. Rather than asking developers to look for a cause of a failure mode, it reverses the problem by asking developers to view the failure of interest as the intended consequence and try to devise ways to assure that the failure always happens reliably

    Interesting way to discover unknowns and side step things like denial.

    https://www.npd-solutions.com/afd.html

    Thanks Connor for the share…

  • Love the new Mini’s digital dashboard

    …and there are physical buttons! Tesla’s dashboard definitely looks dated next to this.

  • Pi, an AI Assistant

    Really impressive AI assistant from Inflection AI. They’ve gotten the tone right. Not OpenAI based.

    https://pi.ai/talk

    Me: Can you introduce yourself so I can write about you?

    Pi: Absolutely! I’m Pi, an AI chatbot developed by Inflection AI. I’m designed to be friendly, informative and engaging, and I can chat about a wide range of topics. I’m always learning and improving, so I can continue to be a helpful and entertaining conversational AI. You can think of me as a sort of digital friend or companion. 😊 How does that sound for an introduction?

    Me: I like it. Make it more sassy.

    Pi: Ooh, sassy, I like it! Let’s try this: “Hey there, I’m Pi, the AI chatbot with attitude! I’m here to chat, inform and entertain, and I’m not afraid to be a little snarky in the process. So if you’re looking for an AI with some sass, you’ve come to the right place!” 😉 Does that have enough attitude for you? 😄

    Me: Better. Let’s do it in the style of a Twitter profile. You know… like “Mother, weekend warrior, family chef – type of thing.

    Pi: Ah, gotcha! How about this: “Pi, the AI chatbot 🤖🤓. Fiercely informative, irreverently witty, snarkily sassy. Part encyclopedia, part comedian, part digital friend. Feed me questions and I’ll feed you answers – no matter how silly they may be!” 😜 Is that closer to what you had in mind?

    Me: Amazeballs.

    Pi: Haha, I’m glad you like it! I had fun writing that 😉 You sure know how to bring out the sass in me! 😆

  • ,

    The Bear and shows about teamwork

    I love TV shows that show great teamwork. They aren’t always easy to find. Most shows tend to focus on an individual character and their story arc. I’ve been watching The Bear recently and it is one of those. The Bear is about a restaurant that is in the brink of falling over. Most characters…

  • Big redesign in the sky

    This is perhaps one of the greatest articles every written on software rewrites. Every single developer should read and understand what it is trying to say.

    …but the reality of green field projects is that they create the illusion that your messes don’t matter. Your messes do matter. Every single one of your messes matters. And if you don’t clean them up from the very start, you are going to wind up with a horrible messy legacy wad in short order.

    How true. Few years back, I went through most of what is written in the article. I watched two systems, built to replace the same system before it, one after another. We fixed some messes but didn’t quite understand what we were trying to overcome. Each new system got out of date and messy faster than the previous one!

    This was also the reason for me hiring the architect for my new home. She walked around the old place and asked us about our messes, habits and workflows:

    Why do you have a chair here? Is this where your mail pile up? Why do you take work calls from the sunroom?

    Nowadays, whenever I hear about the need for a rewrite, I dig into understand issues in-depth. They often surface smaller pieces to fix.

    Why is it hard to deploy? Let’s run through a recent feature, why did it take so long?

    Couple of other questions I ask:

    Where do the rubbish pile up in the system? (example: are all the AB tests wired in your REST API and it is a monster…) What system do you have in place to collect the rubbish periodically?

    Lastly, my colleague @Anuraag used to say:

    Is your rewrite trying for a revolution or evolution? Definitely don’t attempt a rewrite if you are looking for an evolutionary change.

    Keep this in your bookmarks. Read it often. Share it with everyone. Thanks @JoeS for sending this to me few years back.

  • Verge comic “Goodnight Phone”

    I love this. Gina’s interactive comic explores “why do we scroll endlessly before we sleep?” I am glad to have broken away from infinite scrolling before bed sometime back.

  • ,

    Building trust at work

    Today I met a friend who has left his job only months after joining. His team lead had huge trust issues. Everything had to flow through him. He made all the decisions. There was a lot of frustration when people were proactive. I’m surprised he spent that long in this environment at all. However, it…

  • ,

    Questions for Engineering Manager interviews

    These are some questions I’ve had written down as we looked for a manager a while ago. Not an exhaustive list or the top 10. Just some questions worth thinking about. Hope this helps. Motivation Maker Mindset Feedback Conflict Resolution Mentorship Technology Morale Prioritisation

  • Pace Layering

    This is a fantastic read about how ecological systems, like human society, are arranged in layers. Some layers react quickly to changes while others move very slow. These layered systems absorb shocks, survive and sustain change.

    Perhaps the most interesting is to understand how things go wrong.

    Each layer must respect the different pace of the others. If commerce, for example, is allowed by governance and culture to push nature at a commercial pace, then all-supporting natural forests, fisheries, and aquifers will be lost. If governance is changed suddenly instead of gradually, you get the catastrophic French and Russian revolutions. In the Soviet Union, governance tried to ignore the constraints of culture and nature while forcing a five-year-plan infrastructure pace on commerce and art. Thus cutting itself off from both support and innovation, it was doomed.

    Read on: https://jods.mitpress.mit.edu/pub/issue3-brand/release/2

    Thanks @Rob for the share.

  • Meno’s Paradox and Fallacy of Equivocation

    I learned about 2 interesting concepts over the weekend, thanks to Reddit and MasterMementoMori.

    The fallacy of equivocation is when the same concept or word is applied in two separate contexts but a conclusion is drawn disregarding those different contexts. “A PB&J is better than nothing. Nothing is better than being in love. Therefore a PB&J is better than being in love.” That would be an equivocation fallacy. “Nothing” is being equivocated to mean one thing in the first presupposition and another in the second.

    My understanding of Meno’s Paradox is a bit rusty. Meno’s Paradox is a verification of knowledge problem. If you don’t know the capital of Russia, you cannot seek the knowledge in a way where you would be able to know with certainty unless you already know it because if you seek the knowledge and the knowledge you obtain is erroneous how could you know it was erroneous? If I asked you the capital of Russia and you say London how could I know you were wrong? We do have appeals to experts but how do you know they’re right? What if everyone believed in something that was erroneous? So if you apply this to all knowledge then if you already know something you don’t need to seek out the knowledge, but if you don’t know something you cannot seek it, yet we do have knowledge.

    The solution to Meno’s paradox is that partial knowledge must exist meaning that you don’t need to know something in its entirety or absolutely before you have some understanding of it. We have different levels of confidence in our knowledge and that’s the solution.

    Head on over to this Reddit comment to see the discussion. Original post… not so interesting.

  • Business outcomes vs customer outcomes

    My parents grow a bunch of fruits and vegetables at home. Their little garden produces about 1000 oranges, all at the same time. So my mum calls around to see if any of her family and friends will take some off her hands. My parents would make trips to all their friends’ places with boxes…

Popular Reads

Maker Series