Principles of Making

by Dineth Mendis

  • Investing to catchup vs leapfrog

    It helps to find your own path to success. Good read about investing on catchup vs investing to leapfrog.

    …if your competitor’s boat gets ahead of you at the starting line, the instinct is to chase it. To tack where it tacks on the same path. But if you do, you will always be behind, because you will be sailing on the same path, subject to the same wind. And in fact for much of the time, you will be sailing in its ‘dirty air’ — i.e., it gets the full wind in its sails, which breaks the wind diminishing its effect on your sails. Your only hope is for the leader to make a terrible blunder. Otherwise, you will race for hours and hours, tacking dutifully behind the leader and crossing the finish line behind.

    https://rogermartin.medium.com/the-tragic-futility-of-investing-to-catch-up-aaf4b5c90e0f

  • Can AI make art?

    Fantastic article on The New Yorker on “Why AI Isn’t Going to Make Art“. Thought provoking and plenty of good threads to reflect on.

    Article dives into the need to make so many little decisions in order to create something of value. With a prompt, the amount of decisions made are minuscule.

    Even with code generators like Github CoPilot, this has been the issue. LLMs can generate basic code really quickly. It is certainly a great tool for picking up programming or learning a new language. Perhaps it will make a mid-level engineer efficient by 2-3%. However, for a competent coder, it offers little in the way to help solve actual problems. Code’s just an expression of a solution. Solving problems in code require a lot of decision making.

    It also talks about how real connections matter:

    Some individuals have defended large language models by saying that most of what human beings say or write isn’t particularly original. That is true, but it’s also irrelevant. When someone says “I’m sorry” to you, it doesn’t matter that other people have said sorry in the past; it doesn’t matter that “I’m sorry” is a string of text that is statistically unremarkable. If someone is being sincere, their apology is valuable and meaningful, even though apologies have previously been uttered.

    Perhaps my favourite part:

    We are entering an era where someone might use a large language model to generate a document out of a bulleted list, and send it to a person who will use a large language model to condense that document into a bulleted list. Can anyone seriously argue that this is an improvement?

    No, it isn’t.

    https://www.newyorker.com/culture/the-weekend-essay/why-ai-isnt-going-to-make-art

  • ,

    Strategy and focus

    Great quote from “Good Strategy/Bad Strategy: The difference and why it matters” by Richard Rumelt: “If the business is really successful, then there is usually a good strategic logic behind that success, be it hidden or not. But the truth is that many companies, especially large complex companies, don’t really have strategies. At the core,…

    0

  • What kind of principal engineer are you?

    What kind of principal / staff engineer are you? This is a really good guide around what each type of role entails. One of the reasons why a single levelling guideline for an IC is really tough.

    https://staffeng.com/guides/staff-archetypes

    The four common archetypes of Staff-plus roles I encountered are:

    ❶ The Tech Lead guides the approach and execution of a particular team. They partner closely with a single manager, but sometimes they partner with two or three managers within a focused area. Some companies also have a Tech Lead Manager role, which is similar to the Tech Lead archetype but exists on the engineering manager ladder and includes people management responsibilities.

    ❷ The Architect is responsible for the direction, quality, and approach within a critical area. They combine in-depth knowledge of technical constraints, user needs, and organization level leadership.

    ❸ The Solver digs deep into arbitrarily complex problems and finds an appropriate path forward. Some focus on a given area for long periods. Others bounce from hotspot to hotspot as guided by organizational leadership.

    ❹ The Right Hand extends an executive’s attention, borrowing their scope and authority to operate particularly complex organizations. They provide additional leadership bandwidth to leaders of large-scale organizations.

  • Great read: the man who killed Google Search

    …Google’s response to the Code Yellow was to roll back changes that were made to maintain the quality of search results.

    Yikes. It is yet another story about corporate greed destroying a great products. Passionate write up, well worth the read: https://www.wheresyoured.at/the-men-who-killed-google/

    Thanks @Rob for the share. Coverage of Boeing troubles by John Olivier
    was another hot take on good products going astray under new management.

  • A week in Phuket

    A week in Phuket

    Recently, we spent a week in Phuket (Thailand) to get away from our busy work schedules to just chill by the beach. Phuket is an island at the south of Thailand. It is mostly a tourist island with stunning beaches, bright blue waters, great resorts and delicious local food. Here are some pix!

    0
  • ,

    Future of the web

    I recently had the opportunity to attend WordCamp Asia in Taipei. It was my first time in a WordPress community event. One of the key takeaways for me was that WordPress adoption was in decline. Not only that, behind closed doors, I got to hear that number of websites created on the web overall is…

    0

  • Euclidean distance vs Cosine Similarity for text searches

    Good article on the topic: https://cmry.github.io/notes/euclidean-v-cosine

    Cosine similarity is the angle between two points, while euclidean distance is the actual distance between two points. Cosine doesn’t care as much about magnitude so does well for different lengths of data (think how far into a specific direction something is as long as they are in that direction).

  • Watch: Pantheon

    Great show about living forever. Best sci-fi show I’ve found this year. Check it out!! IMDB

    0
  • ,

    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.…

    0
  • , ,

    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:…

    0

  • 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,…

    0
  • , ,

    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…

    0

  • 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.

Popular Reads

Maker Series