/reader

I can easily imagine a spirited debate where some folks disagree with any or all of my points, arguing that they should be struck as guidelines from our collective ethos of craft. Perhaps some are boring, or too opinionated, or too reliant on trends. There are lots of valid, defensible reasons.

I can easily see this discussion being an exercise in frustration, where we debate for hours and get nowhere — “I suppose we can all agree to disagree”.

And yet — thanks to a link to Codex’s front-end tool guidelines in Simon Willison’s article about how coding agents work — I see that these are exactly the kind of guidelines that are tucked away inside an LLM that’s generating output for many teams.

It’s like a Trojan Horse of craft: guidelines you might never agree to explicitly are guiding LLM outputs, which means you are agreeing to them implicitly.

It’s a good reminder about the opacity of the instructions baked in to generative tools.

We would debate an open set of guidelines for hours, but if there’re opaquely baked in to a tool without our knowledge does anybody even care?

When you offload your thinking, you might be on-loading someone else’s you’d never agree to — personally or collectively.

Reply via: Email · Mastodon · Bluesky

What we truly need is focus.

No notifications, no doomscrolling, no catching up on shows or podcasts, no checking if the feed reader says “All read”. Just a few minutes dedicated to writing, nothing else.

That small shift makes all the difference. Fifteen minutes of focus will produce more words than an hour full of distractions. And it feels ten times more satisfying.

Try it for a week and you’ll be surprised. Try it for a month and you’ll wonder why those other things ever felt so important. Try it for a year and you’ve written a book.

All thanks to one simple change. Focus.

It reminds me of something Paul Ford said:

The most brutal fact of life is that the discipline you love and care for is utterly irrelevant without the other disciplines that you tend to despise.

Ah yes, that age-old mindset where you believe your discipline is the only one that really matters.

Paradoxically, the promise of AI to every discipline is that it will help bypass the tedious-but-barely-necessary tasks (and people) of the other pesky disciplines.

AI whispers in our ears: “everyone else’s job is easy except yours”.

But people matter. They always have. Interacting with each other is the whole point!

I look forward to a future where, hopefully, decision makers realize: “Shit! The best products come from teams of people across various disciplines who know how to work with each other, instead of trying to obviate each other.”

Reply via: Email · Mastodon · Bluesky

Problem was, I didn't really know how I was going to redesign the site. Then, one day, I was talking with Sven via email and I visited his blog (also running Pure Blog for the record 🎉), and I immediately knew that was the kind of design I was looking for. It's simplicity is just lovely, and so easy to read.

So I set about making my own version of Sven's lovely design. I didn't want it to be exactly the same as his, but I also didn't think my design would turn out quite as close to his as it did - I suppose that goes to show how much I like his site. :-)

I've spoken to Sven and he's good with me effectively copying his design.

For posterity (as I'm likely to change it again in the future) here's what the design currently looks like:

I'm still not 100% sold on the font (but it is growing on me), and I'm not sure about the yellow in the header, but blue everywhere else. So I may change a couple of things subtly. Having said all that, overall I'm the happiest with the design I've been since moving to Pure Blog.

Finally I'd like to thank Sven for allowing me to steal his wonderful design.

What do you guys think? Leave a comment below, or reply by email.

Thanks for reading this post via RSS. RSS is ace, and so are you. ❤️

You can reply to this post by email, or leave a comment.

Summarizing, AI sounds like a incredible genius synthesizing the world’s knowledge right up until you ask it about the thing you know about, then it’s an idiot. Even knowing about this phenomenon and having experienced it countless times, LLMs have an intoxicating quality to them.

If there’s one thing LLMs do well, it’s delivering an enormous blast of dopamine if they do a good job on the first try. That “if” does a lot of heavy lifting, but when it happens you start to believe the idea that the multi-modal chat box could make you faster and infinitely capable. A hop and a skip and hundreds of dollars in tokens later, you made something that would take lifetimes of learning to create.

The marketing around Generative AI is that every person can be their own Designer, Developer, Researcher, Content Writer, Video Producer, and Podcast Editor. With the right skills.md files everything will fall into place. We will automate all automatable tasks. The experience will be “frictionless”.

You’ll be able to automate away the jobs you don’t enjoy…
And the jobs you don’t know how to do…
And the people who do those jobs…
The people you don’t enjoy…

You won’t need to talk to or wait on anyone. You can automate away anything or anyone that stands in your way. You will reduce costs. You will be richer. It will be frictionless.

Sometimes I feel like there’s a palpable tension in the air as if we’re waiting to see whether AI will replace designers or engineers first. Designers empowered by AI might feel those pesky nay-saying, opinionated engineers aren’t needed anymore. Engineers empowered with AI might feel like AI creates designs that are good enough for most situations. Backend engineers feel like frontend engineering is a solved problem. Frontend engineers know scaffolding a CRUD app or an entire backend API is simple fodder for the agent. Meanwhile, management cackles in their leather chairs saying “Let them fight…”

I think it’s a dangerous place to be when we start to consider people as friction.

That’s because we know Gell-Mann is real. We know there’s an optimism bias the size of the sun blinding us to the actual quality of what the machine is producing. We need knowledgeable people to share what they know to improve the quality of our work, generated or otherwise. We even need ignorant people to make sure we can break ideas down into their simplest form that everyone, agents or human, understand. People can have bad attitudes, be shitty, and have wrong opinions… but people are not friction. An LLM may be able to autocorrect its way into a plausible human response, but it’s not people. It doesn’t care if it’s right or wrong. The money and hype surrounding it acts as a shield to its reputation. LLMs make up answers if it doesn’t have enough context and they fall over if it has too much context. It amplifies good patterns the same as bad patterns. And it glazes you with flattering language the entire time so that chart go up.

People, the context-bearers, have experience and capabilities that machines might never understand encoded in our muscles and memory. I’m on record saying I despise nuance –and I do– but it’s more important than ever to be able to connect to our fellow humans over this nuance so our world is not paved over by contextless opinions from ill-informed robots. Empower and believe people over machines.

A bit about my background. I come from a working class lineage, through my grandparents and beyond. Well, that's being generous about my dad's family, which might be better described as "working-when-not-drunk class." There are some professionals here and there among the aunts and uncles and cousins but my direct line is all laborers, secretaries, and cooks (not chefs!). My mom worked in entry-level medical and clerical jobs. My dad worked at the French Lick hotel in the bad old days, before it was restored by the Cook family. He also worked on the railroad before a disastrous accident that ruined his back. Eventually he got a HVAC certificate at Ivy Tech and worked a few years at a local HVAC company (whose owners moonlighted as a Southern Gospel quartet) before getting on at the Ford factory in its declining years. He worked there until his death; it moved to Mexico not long after. I resonate with Wendell Berry's disdain for James B. Duke because I feel the same way about Bill Clinton: unforgetting, unyielding contempt because of what he and his rich friends did to my family and community.

I was encouraged to get an education, in the practical "get a good job" sense. They were excited for me when I started on the pharmacy track at Butler University. Alas, organic chemistry and romance ended those hopes: I quit after my sophomore year because Rachel was the only future that mattered. I started looking for delivery jobs simply because I liked the delivery job in high school. That led me to interview for a shipping and receiving job (delivery adjacent!) in a small manufacturer. While I was interviewing, the guy said "You know, we just had an office job open up today and I think you're better suited for that." Swallowing my offended feelings, I accepted an accounts receivable job.

At some point I had put my name in the lottery for a job at the Ford factory. While I was working in AR at the manufacturer, I got a call from Ford. (Rachel, was that call actually offering me the job or only offering me an interview? My memory is fuzzy, as usual.) At that point in the factory's history, they weren't really offering the full-time, union-benefits jobs. You could work your way into those but a job at Ford/Visteon was no longer a guarantee of a solid, middle-class living. My dad didn't love the idea of me working in a factory, especially since it no longer offered a secure future. My pastor also thought I should "do something more" and encouraged me to finish my degree. I turned down Ford/Visteon and started night classes in accounting. Why accounting? Because I was working in accounts receivable. Imaginative, right?

Eventually my employer closed the manufacturing business and I got a job at a big nonprofit doing data entry in the accounting department. I eventually finished my BS in Accounting, slowly worked my way up in the accounting department, took several more classes, became a CPA, became the assistant controller and then interim VP of accounting for a few months before I quit and took my current, intentionally downsized job. Embrace downward mobility, as I told a friend recently.

One of the main reasons I embraced downward mobility was contemporary work culture. As I mentioned before, and as you can see from my history, I've never been a product of the right acculturating institutions. I didn't graduate from the sort of "b-school" that had alumni networking events; it was the sort of school that advertised on daytime TV for people who were "unemployed or underemployed, or looking to turn their career around."

I don't read business books and I don't listen to podcasts instructing me on how to be a "people leader." I don't admire CEOs or entrepreneurs (quite the opposite). I steadfastly refuse business lingo. The goals and lifestyles of those who are successful in this work culture are utterly strange to me, like I'm visiting another planet. For this I am thankful.

Despite my occasional dream of a liberal arts education, my actual educational experience has been eminently practical. Years ago I said I was a white-collar worker with a blue-collar heart--and I think that's more true than ever. That's not to say I didn't pick up some affectations along the way. For a long time the "do something more" idea remained a part of me and I thought of myself as an aspiring intellectual. Thank God that's over. I'm still scraping off some barnacles here and there but I've made peace with who I am and, more importantly, where I come from. In true second-half-of-life fashion, this work of reclamation is the task that matters now.