Paul Watts

🏎️💨 Making of a Ridiculously Fast™ API client in R. Why my package is **~17x faster** than the community alternatives that call the **exact same API endpoints**. 👇🏽**design choices matter** ✨ https://lnkd.in/ggi_2XyQ

129

2 Comments

Mermaid diagrams are now available in Notion, Obsidian and VS Code. It's fast becoming the default Markdown format for diagrams. Mermaid is great for quick flowcharts, but the real power is that the format is fairly straightforwards to populate from dynamic data (such as a spreadsheet or database). We have a lot of complex business logic and process flows in the Icehouse Ventures investment app, so we threw together a quick open source package for using Mermaid in Laravel: https://lnkd.in/dda6tBag

16

4 Comments

Dev agencies, if you don’t want to be treated as a commodity, stop acting like one. - Learn the business context for engineering needs - Stop squeezing your clients every opportunity you get - Prioritize transparency, communication, and accountability In short, position yourself as a partner that uses tech to solve business problems. You really can’t complain about being seen as a commodity if you treat everything as a transaction.

1

1 Comment

From the scrappy pre-seed, stealth-mode team of 2 through to fast-scaling Series C/D companies with many, many millions in the bank, each startup brings its own excitement and challenges. Of course, hiring strong technical talent is *always* important, and that’s a challenge in itself. But there’s also a certain nuance around the “people fit,” especially in the earliest stages. And I’m not necessarily talking about culture add/fit. The main thing that comes to mind with this, and one of the biggest things I drill down on with candidates, is motivation to join a company at the beginning stage. It’s absolutely not for everyone, and that’s okay!! The second thing that comes to mind is being radically transparent with candidates about what’s under the hood at the startup they’re considering. There’s no point in sugar-coating or selling a dream that doesn’t exist. Even in the most innovative and exciting startup there’s bound to be some cons to joining. It’s the nature of the beast that is startup land. Give the full picture, the right candidate will be excited regardless. Getting as much as you can out in the open in your initial screens and interviews, and re-checking on how folks are feeling throughout the process, is one of the things I feel is not spoken about as often yet is so important! (+ a good way to minimize cold feet/drop outs!)

23

5 Comments

One reason I pulled yesterday's post out of what I'm writing for the book is that salary is almost a separate book on it's own - and one likely better written by somebody else. In my own career managing software engineers, I've seen it handled so many different ways: - When working for a very large media company, I don't recall knowing the salaries of my team. Instead, I worked in percentages that were tied to performance bands. - A few other times, I had approval, but the salary adjustments happened in HR or at a departmental level above me. I communicated the adjustment along side a review (usually), but didn't make the decision. - Another time, I got a spreadsheet with the team, their salaries, and a bucket of additional cash I could spread between them. So, right-sizing one salary might mean short-changing somebody else - unless I went back to HR and tried to make the bucket bigger. Each company has handled salary adjustments (and starting negotiation, but that's a chat for another time) differently, giving different levels of autonomy for their direct managers. These constraints and context aren't always communicated to the team - I can't recall if I ever shared this with them, for instance. If you've managed folks, how much control have you had over their salary adjustments when the time came? And did you wish you could tell them how little you had?

5

1 Comment

BDD vs. Traditional Frameworks: A Comedy 😂 Act 1: The Skeptics: "BDD? Gherkin? More work for no reason! I'd rather wrestle a kraken than write in plain English!" Act 2: The BDD Evangelist: "Hold on, my friends! BDD is like a well-organized toolbox, not a kraken's lair. Let me show you the light!" Act 3: Separation Anxiety (Solved): "With BDD, test cases and code are like a happily divorced couple – living separate lives but still getting the job done. No more Frankenstein test methods!" Act 4: Reusability Rhapsody: "Steps are like LEGOs – build once, use everywhere! Traditional frameworks? More like a jigsaw puzzle with missing pieces." Act 5: Hooks – The Heroes of the Hour: "Logging, cleanup? BDD's hooks swoop in like ninjas and handle it all behind the scenes. No more code clutter!" Act 6: Onboarding Nirvana: "Newbies, rejoice! BDD specs are your onboarding manual. Learn the features, copy the steps, become a testing superstar in no time!"

3

1 Comment

There is a $7.5B company that: • Started with $0 funding • Has 100M+ active users • Generates $1B+ in ARR And now powering the open-source revolution. Here’s the story of GitHub: Tom and Chris were both working at CNET when they met in the mid-2000s. They were both passionate about software development and knew that developers needed better tools to manage and share code. In 2008, they started working on a side project that would change their lives. Git was a version control system at the time. But it had terrible UI and no functionality for collaboration. Their idea: build a web-based platform to host the Git repository. It would revolutionize the way developers collaborated on code. They launched GitHub in April 2008 with just a handful of users. Early on, they bootstrapped with an intense focus on customer experience and on exceptional UI. And they fully embraced the open-source community. The commitment paid off... Three years later, they had over a million developers on their platform. GitHub became the focal point of the open-source revolution. Hosting and collaborating on code was never so easy. Even big tech (FB, MSFT, Google etc) became customers. From there things skyrocketed 👇 By 2012, the biggest VCs started noticing. GitHub raised $100 million in Series A funding led by Andreessen Horowitz Their growth was explosive. By 2015, they had 9 million users and hosted over 21 million repositories. How did they scale so rapidly with a relatively small team? Simple answer: They leveraged talent all over the world. GitHub adopted a distributed team model early on, hiring talented developers from around the world. Scott Chacon, a co-founder, worked remotely from Mexico, setting the precedent for a global workforce. GitHub attracted top talent from regions like Eastern Europe etc. GitHub's distributed model also allowed for continuous development cycles with teams in different time zones. By 2018, GitHub had revolutionized the developer experience. And Microsoft bought them for $7.5 BILLION. All the co-founders are billionaires. Not bad for a side project. GitHub, WhatsApp, Wayfair and many giants were built on global talent. Trained pros take on rote execution at a fraction of the cost, while top teams focus on strategy and product. GrowthAssistant embeds elite, college-educated pros from the Philippines directly on your team. We find and place talent with the EXACT skillset you need. DoorDash, HubSpot, True Classic, and 200+ others use us Check it out:

23

2 Comments

Consolidated my Notion homepage on a custom domain. I'm surprised it's not yet a native feature. I've realised that while pointing my personal website (https://angeloreale.com), I had lost most of my few years old SEO authority. So then, ... we just build it again. :) Recommending this Notion wrapper, and here is my referral link (I get some bucks if you sign-up using it): https://lnkd.in/dNKCuppi

Q: "How do I know if my team is delivering secure software? I’m a non-technical founder without the budget to hire consultants." A: Well, you can’t know for sure. If you don’t know what’s good, you can’t know what’s bad either. But you’re not helpless. It’s quite safe to assume that your average general-purpose developer will deliver similar quality across the board. A sloppy developer will be sloppy regardless of what they do. It’s not likely their approach to security will be spot on, but it’s only the quality of the frontend that’s terrible. So if you’re not sure about security, take a look at other, more relatable parts of their work and do the guesswork. It’s unlikely you’ll be very far off. Talent is only one piece of the puzzle. The other is character. The character and job habits of people working for you are a good proxy for overall quality. I had this guy who wasn’t really good at certain development concepts, and his code reflected this struggle. On the other hand, he always delivered properly tested, stable, solid work, and on time. His character didn’t let him send off stuff he wasn’t happy with. As a non-technical founder working with tech teams, you’re always in a situation of information asymmetry. Some dudes are working for you and telling you stuff you have no idea about, and you have no choice but to trust them. You can’t bridge that gap with knowledge - at least not quickly. But what you can do is look at the problem holistically, listen to your gut feeling, and go with it.

7

3 Comments

Big tech isn’t just built on code, it’s built on trust. Back in 2010, Mark Zuckerberg wrote an internal email. Asking for the resignation of someone who leaked confidential plans. Here’s why this is still relevant in 2024: ↳ Leaking private company info isn’t brave, it’s destructive. ↳ Transparency builds trust, not at the expense of confidentiality. ↳ Trust is the foundation of innovation; without it, even giants fail. This document is from Facebook’s Little Red Book (2012). Let’s break it down: Confidentiality is foundation of progress. ↳ Every innovative idea starts in private. Betrayals, like leaks, affect everyone. ↳ Cleaning up these messes wastes time. Open cultures thrive on trust.  ↳ Once trust is broken, the team suffers. What can we learn from this? Protecting your team’s trust and vision is everything. Whether you're leading a startup, or a billion-dollar company, don’t be the one who destroys progress for short-term gain. Will you take a stand on trust? ♻️ Repost if you agree that culture starts with trust. ✚ Follow Maria Matloub more on leadership, innovation culture & AI.

81

67 Comments

Okay, the yew abstractions just weren't worth the complication for me, imo. It's not so bad to just write my own #javascript and call the wasm_bindgens directly after all: https://lnkd.in/gifgcT4c I've repeatedly seen the pattern that backend programmers make javascript more complicated than it needs to be, and I think that might only get more extreme with #WebAssembly being a thing Watching all the evolutions of Rails js over the decades (as someone who has been writing extensive js since gen 4 browsers) has been painful at times. Trunk (trunkrs.dev) is still super useful though, as well as the rest of the rust wasm stack I'm using. mast:https://lnkd.in/gj798twP

3

On in-house systems I’ve seen this so many times; the team did all their testing in-house and they didn’t build automated regression tests because they didn’t want to spend the money on it. Read more 👉 https://lttr.ai/ARljS #softwaredev #SaaSBusiness #InHouseApp #SaaS #BusinessBuilding

2

“You’re leaving software engineering to start a paper straw company??” Jordan and I came up with the idea of creating the world’s best paper straw in early 2019. I was working as a Senior Software Engineer and always thought I’d start a SaaS tech company — not a physical product one. We officially incorporated SOFi Products in March of that year, but it was still just an idea. Jordan focused on product development, while I had to manage aspects that were new to me: Supply chain and logistics. Exactly eight months later, we launched the SOFi straws in November, taking our idea to market. We went through countless iterations during that time but ran into a new challenge. On the one hand, we had this product that lasted for hours, didn’t get soggy, or tasted like paper; on the other hand, we now had to sell it. How do you stand out in a crowded sea of straws claiming to be “compostable”? Most entrepreneurs say, “Build it, and they’ll come” — the truth is not so straightforward. We had to learn sales. I felt like we were really scrambling until I came across a book called Predictable Revenue. The author outlines a systematic approach to generating leads, prospecting, and structuring teams for success in the book. A quote from the book that completely transformed our sales was, “No is just a future yes.” You will face rejection on a daily basis and you need to become comfortable with rejection if you want to succeed as an entrepreneur. Fast forward five years, and we’re present in every Canadian province and 47 US states!

22

2 Comments

I'm so excited about the problems "traditional" software companies are tackling right now. LLMs let software teams move faster, make sense of larger domains, and built much more complex tech than we were able to even five years ago. I believe the impacts in healthtech, govtech, and fintech will be large. Simultaneously, I'm amazed at all the ways one can lose money investing in AI companies - especially the foundational models. There's no part of this market that isn't trending toward commoditization. This has been true for a while but the release of llama3.1 makes it especially clear: Most workflows can retrain on this open-weight 405B model with no change to their budgets (AWS Bedrock charges *at max* the same as OpenAI) and then find ways to negotiate/optimize that cost way down while not sending their data away to a 3rd party. Even the B2C story is commoditized — what AI wrappers have believable ROI if I can run this one-liner and the hard part is accomplished for a fraction of a cent?: aws bedrock-runtime converse --model-id meta.llama3-1-405b-instruct-v1:0 --messages '[{"role":"user","content":[{"text":"Write me a post enumerating how investments in LLMs may yield no competitive advantage."}]}]' As I look past the flashy parts of AI I see: * Building one-off tools against novel APIs is now (and forever) instant * Analyzing requirements for most tasks and understanding new domains is an order of magnitude faster * GitHub Copilot yearns to write React for us * LLMs give the same boost as pair programming at zero cost I haven't been this excited to build complex products in a long time.

36

1 Comment

Will Devin AI replace developers? 😱 Maybe 🤷🏻‍♂️ To me personally, Devin is a development tool and not a replacement...YET 🌚 I am not denying that Devin can code really well if all the claims are accurate. Eventually, it may replace developers. But developers don’t code just to code. We build products ✅ We build solutions ✅ And these happen to be made of code. Can companies ditch all developers today and expect products to still get built and maintained to the same standard as an enterprise-level solution? Nope 🙅🏻‍♂️ The quality of a product refers to how well it solves user problems. And those gaps between code, user, and solution? That’s where good developers provide values 👨🏻‍💻✨

1

Found this on The Pragmatic Engineer's Substack, and had to share as it does provide a ton of context as to why the pay range for some roles is so dramatic across different companies. "Local companies (Tier 1): most local businesses that benchmark to the numbers on most salary comparison sites. They usually offer close to – and sometimes slightly above – what government positions advertise for senior engineering roles. Ambitious local companies (Tier 2): startups, scaleups, and more ambitious local companies that want to hire and retain the best people, locally. Companies benchmarking across a region (Tier 3). Big Tech companies, hedge funds and scaleups that hire across regions, frequently hire from abroad, and often compete with fellow Big Tech giants for talent."

3