Tag: Frugality

Wash, Rinse, Repeat

Wash, Rinse, Repeat

By | | Comments 1 comment

Well into my twenties I was a picky eater (for a while as a kid I didn’t even like pizza), but thankfully those days are over. Now I’m a fan of many cuisines, and I especially enjoy fine dining experiences. White tablecloths, unique pairings, quality over quantity, that sort of thing. Admittedly, sometimes at first glance I wonder if it’s enough food, but inevitably I find that by the time I’ve eaten everything I’m full. Portions may be small, but they’re rich in flavor, with little filler. Having more in one sitting would be too much.

A sampling of meals from my summer trip to England

Further, I don’t believe meal after meal of fine dining would ultimately be either pleasurable or healthy. The experience is sensorily dense (and expensive); having space between experiences is a critical to sustainable enjoyment.

An oft-repeated benefit of AI (especially by those of us who sell it) is that it will reduce rote work so that humans can focus on what needs truly human judgment. Sounds good, right? Especially if you’re a leader concerned with an ever-growing backlog and an ever-tightening budget around staff to attack it (in my field of government work this is incredibly common). But there’s a problem.

Just like the stomach has a limited capacity for culinary complexity, the brain has limited capacity for decisional complexity. Constant deep thought without mental rest is a path to all manner of bad outcomes, for individuals and the business objectives they’re supporting. All sorts of work, normally conceived, includes a rhythm of push and pull between effort that requires focus and that which is rote:

  • coming up with a business idea and then filing the paperwork to form an LLC
  • authoring the text of a document and then applying formatting cleanups
  • implementing functional logic and then surrounding it with boilerplate code
  • formulating a tax strategy and then pulling together supporting documentation
  • cooking a complex meal and then cleaning up the dishes afterwards

Of course it’s possible for work to be constantly mundane, and automation that relieves the burden of boredom is a good thing. But the elimination of all rote work? I’m not convinced. We may actually need mundane activities to stay healthily effective.

Memento Mori

Memento Mori

By | | Comments 0 Comment

It’s 2019, I’m in Seattle, and my new Amazon boss and I are sitting down for lunch. I hadn’t gone through an onboarding process in some time, and never one at a company that large (my prior employment tenures were 11 and 5 years, respectively). His advice was sound: “it’s going to take a year before you’re comfortable, and that’s okay.”

Onboarding is hard, no matter how long you think it should take (but please don’t call it drinking from a fire hose). Can you even imagine what it would be like to have to completely re-onboard on the regular? Sounds pretty awful, as the film Memento makes abundantly clear.

This is exactly the experience of an LLM. Every. Single. Time.

Setting aside if there’s an “experience” there in any meaningful sense (though if there is, we should pay attention to Steve Yegge), the above has a huge implication for coaxing the best results from AI. Managing context is about much more than raw quantity of and access to data. Those are reasonably solved problems with massive context windows and tool use, respectively. Now it’s about the quality, accuracy, and timeliness of the information that an LLM “pays attention” to.

If your connected SharePoint’s a mess, full of documents long stale (including all those important_v2.3_final_FINAL.docx gems), if you have a whole bunch of dead code in your git repository, and if your agentic tool has written memories from wandering conversations full of evolving ideas that now contradict themselves (as dialog is wont to do if my own experience is to be believed), an LLM is going to get confused. No different than a new hire who has to wade through similar flotsam with no institutional knowledge of what actually matters.

The thing about an onboarding human being is that eventually, through social cues and sheer determination, they will develop their own mapping layer that separates the wheat from the chaff. LLMs have no such advantage.

The machines have not made thoughtful data curation obsolete. Quite the opposite. The good news is that the machines can help with organization also, including leaving notes for their future selves (like Leonard Shelby’s tattoos). You just need to ask. Do that regularly, add a healthy dose of your own efforts, and the dividends will compound.

Calling Me To Shine

Calling Me To Shine

By | | Comments 0 Comment

When the topic recently came up about scheduling a weekly team sync call, to the chagrin of a few colleagues, I suggested 7am PT on Mondays. Given how most of my work is tied to Eastern and Central time, I’ve become accustomed to waking up early. Even on weekends (I’m writing this on a Saturday and I was up about 6:30, for example).

I get that it doesn’t work for everyone, but for me, early mornings are ideal. They also make an excellent subject for a song (this one’s been a favorite of mine since 2006):

Headquarters (Part 3)

Headquarters (Part 3)

By | | Comments 0 Comment

Just when you thought there couldn’t be more (oh trust me, there’s more), here’s comes another round of my series on computer setups (earlier posts are here and here).

Years: 2005-2010
Machine: The box in the closet from my last post but with a snazzy new LCD monitor (my first flat panel), wireless peripherals, and my wife’s great-grandmother’s writing desk.
What I was doing: writing daily on Xanga; applying to family camp; traveling to Tennessee to watch Revenge of the Sith with a high school friend; hosting LAN parties for Age of Empires III; traveling a lot for work.

Years: 2006-2007
Machines: A plethora of cast-off parts coalesced into a couple functional boxes in the garage.
What I was doing: running a NAS for storing all my media; trying to get Gentoo Linux to compile; realizing that running a bare web server on the Internet is asking for trouble.

Years: 2008-2010
Machines: A beefed up HTPC rig in a rackmount case with a whole bunch of amps to power my Magnepan speaker system, plus the plethora of beige boxes from before, but better arranged.
What I was doing: shivering in the garage when using this desk in the winter, listening to Comfortably Numb at peak volume, hosting movie-watching parties.

Year: 2011
Machines: Same rack mounted setup, but relocated from our old garage in Ohio to a closet in our new garage in San Diego, plus a random beige box (those just won’t go away).
What I was doing: Playing with some audio recording gear; streaming Game of Thrones; stocking up on printer paper, apparently.

Years: 2012-2014
Machines: Moved inside, and rebuilt the guts from the rack mount case into a traditional one (albeit black and silenced), also got my first Mac laptop (from which I’ve never looked back).
What I was doing: writing election software; creating hand-made guitar effect pedals (that were terrible); developing back problems thanks to a crummy chair.

Like Riding A Bike

Like Riding A Bike

By | | Comments 0 Comment

Yesterday I re-passed the AWS Certified Solutions Architect – Professional exam. It’s my third time taking it (2019, 2022, and now 2025). I went into it cold turkey, absolutely zero preparation, and while my score wasn’t as good as before, a pass is a pass.

I guess at this point, I’ve done enough work in AWS that the knowledge is pretty much permanently ingrained. It reminded me of this article on Buying Moves:

There’s an amazing quirk of the human body that makes fitness adaptations work a bit like powerups in a video game. You can spend some resource to add capabilities to your “character,” and if you do it right they’re always available to you (for the most part). I’m talking about muscle memory and our ability to “lock in” physical skills.

Perhaps there’s a mental version of the same phenomena?

Speaking of that link, being one myself, I’m a big fan of True Generalist. While it isn’t for everyone (and that’s okay), I can’t disagree with his take on competencies that every person should have, and further skills that generalists need to function effectively. Both worth a read if you’re this type of person.

Headquarters (Part 2)

Headquarters (Part 2)

By | | Comments 0 Comment

Continuing from earlier, this post covers early adulthood, pre-kids.

Year: 2000
Machine: Custom built beige box with NewEgg parts
What I was doing: Enjoying early married life; playing Deus Ex; renting movies from Blockbuster and watching them on my computer’s DVD-ROM drive; organizing documents in that green file box (which I still have).

Year: 2001
Machine: Same beige box but with new guts
What I was doing: starting to explore high-end audio and home theater, applying to Ph.D. programs, anticipating The Fellowship of the Ring.

Years: 2002
Machine: Still the same beige box but a new “flat” monitor
What I was doing: trying to understand Topology, skipping graduate school classes to play Diablo II; anticipating The Two Towers (I still remember waiting for this trailer to download… it was was mind-blowing, despite the low quality of the day).

Year: 2003
Machine: You guessed it, a beige box, though I believe I’d upgraded it yet again
What I was doing: starting a blog on Xanga, anticipating The Return of the King (it was on this setup that I created a postcard inviting 40 of my closest friends to a private midnight screening at the Arena Grand).

Year: 2004
Machine: A second beige box filled with scraped together cast-offs from my main computer, complete with double optical drives
What I was doing: embracing my minimalist tendencies by trying to hide boxy components inside closets and running cables through the walls; ripping my entire CD collection to FLAC; preparing for our first kid.

Going Small

Going Small

By | | Comments 0 Comment

I’ve been an Android user since the original Motorola Droid was released back in 2009. However, last month I finally broke down and made the switch to iOS.

I didn’t buy new, though. Because I don’t like big phones, I found myself a refurbished iPhone 13 Mini. It’s perfect. Sure do wish Apple would acknowledge the ongoing market for small devices, but it seems they’re well and truly dead. Maybe I should get a second Mini as a backup, especially since I’m case-free?

Go With It

Go With It

By | | Comments 0 Comment

Last week I finished The Principles of Product Development Flow, based on a recommendation from the article I wrote about in Fightin’ Words. To say it was relevant to my current line of work is an understatement; I immediately mailed a copy to our de facto development process person.

Luckily for us all, though, there’s an official TL;DR version online. It’s a plethora of pithy principles packed onto one page. Go check it out!

In A Nutshell

In A Nutshell

By | | Comments 0 Comment

Of the various AI-powered chat tools out there, I’ve been leaning into Claude the most. I appreciate their stance on safety for one thing, and I also really like features like document uploads, shareable projects, and artifacts.

Yesterday I exported the entire contents of this blog, loaded it into Claude, and then asked it to summarize my career trajectory.

Based on your blog posts, your career trajectory can be summarized as follows:

1. Early Years (Ages 4-18):
   - Started programming at age 4 on a TI-99/4A computer
   - Self-taught BASIC, then learned C and Pascal
   - Developed various small projects and games

2. College Years (Ages 19-24):
   - Studied mathematics and computer science
   - Worked on academic projects, including computational mathematics

3. Early Career at Defense Contractor (Ages 22-34):
   - Started at TRW (later became Northrop Grumman) right after college
   - Worked primarily with Ada and C
   - Developed algorithms for terrain analysis and flight path optimization
   - Gained experience in mapping software and API design
   - Moved to San Diego and got first taste of technical leadership

4. Mid-Career Transition (Age 35):
   - After nearly 13 years at Northrop Grumman, moved to Everyone Counts
   - Transitioned to working with Java and Perl
   - Became technical lead for the company's voting application

5. Technical Growth Period (Ages 36-37):
   - Expanded skillset to include Angular, Node.js, and Docker
   - Focused on continuous learning and adapting to new technologies

6. AWS and Cloud Focus (Age 38 onwards):
   - Joined Amazon Web Services as a Senior Consultant in the public sector
   - Obtained multiple AWS certifications
   - Worked extensively with cloud technologies and services

7. Leadership Role (Recent):
   - Became a technical manager, leading a team of software engineers
   - Focused on both technical and people management aspects

8. Current Role (as of last blog post):
   - Chief Technology Officer at Research Improving People's Lives (RIPL)
   - Working at the intersection of technology and public policy

Throughout your career, you've consistently demonstrated a passion for learning new technologies, solving complex problems, and gradually taking on more leadership responsibilities. Your trajectory shows a progression from low-level programming to high-level system design and management, with a growing focus on cloud technologies and public sector applications in recent years.

That’s surprisingly accurate! Well done, Claude.