Category: Writing

Posted on

Revisiting Morning Pages

I discussed morning pages just over one year ago when I was one month into the practice and, as it turned out, one month away from dropping it. My last set of morning pages was July 27, 2024.

I’ve been in a creative rut over the last couple months, often writing blog posts last-minute, not making progress on other projects, and not even taking time to read consistently. It’s hard to pin down a cause but that doesn’t mean I couldn’t try a treatment. I’ve written 1000 words of morning pages each day of the past week, having made two changes that I hope will help it stick.

First, I created a simple shortcut on my phone, iPad, and MacBook that builds a new morning page sheet in Ulysses, requiring only a single tap (or click) to begin writing. This reduces any potential friction in the process and, by adding the shortcut to my home screens, keeps the process in mind immediately upon waking up. Even when I consciously choose to complete some or most of my morning puzzles first, I won’t push it back too far.

Second, I’m treating these morning pages as less of an additional journal and more of an exploration of my creative brain. I definitely get out thoughts related to recent events and day-to-day miscellany, but I want to treat morning pages as a space for my brain, unencumbered by a long day, to let loose and find elements of my creative voice that I’ve misplaced. I’m using to freely explore new blog post ideas, play with perspectives and literary devices to make them more engaging, more of what I want to read. Having a goal beyond mental decluttering has made the time feel more worthwhile without putting additional pressure on the concept.

Even after a few days I can sense my brain is refreshed and excited to tackle projects old and new. A year was too long, but I’m glad I decided to restart regardless.

Posted on

The Lyttle Lytton Contest

This delightful contest celebrating the command of language by constructing concise opening sentences to hypothetical novels bursts into my awareness each year as internet denizens share the best (worst?) entries. Nominees display subtlety and nuance by brazenly breaking as many written and unwritten literary rules as possible with fewer than 200 characters.

This contest appears built for social media, despite starting in 2001. It drives to the core of good and bad writing by isolating a single sentence, perhaps two, given only the context that it begins a book you’ve just plucked off the shelf. The analysis of each worthy submission is deep and, most importantly, funny.

Read about this year’s winners and chuckle along.

Posted on

The New Behemoth

Just as the brazen giant of Greek fame,

With conquering limbs astride from land to land;

Here at our sea-washed, sunset gates shall stand

A fearless leader with a torch, whose flame

Is the unleashed misery, and his name

Torment of Exiles. From his warding-hand

Burns world-wide scorning; his wild eyes command

The air-bridged harbor that twin cities frame.

“Bring, ancient lands, your storied pomp!” cries he

With blazing lips. “Take back your tired, your poor,

Your huddled masses undeserved to breath free,

The wretched refuse of our teeming shore.

Send those, the richest, fortified to me,

I lift my lamp beside the golden door!”

With thanks and apologies to Emma Lazarus.

Posted on

My First Article For the SABR Games Project

I rejoined SABR a couple of years ago and focused my volunteer work on fact-checking articles for the Games Project. These accounts of past MLB games are notable in some context of the author’s choice. They could be historically impactful, meaningful within a player’s career, highlighted by a rare event, or any other such factors that make an otherwise mundane day in baseball history something worth remembering.

Last month I decided to try writing one of these articles. I trawled through the archives of Minnesota Twins history for interesting seasons and landed on an early game in 2009 that defined the year for Jason Kubel.

You can read the article here.

Posted on

Review: An Update on LLM Satire

I gave Claude (3.7 Sonnet) the same prompt I provided ChatGPT two years ago: Write a short article in the satirical style of The Onion, titled “Optimistic AI Just Happy to Be Here”.

I also went back to ChatGPT to see how it has improved.

Claude’s attempt.
ChatGPT’s attempt.

This test encapsulates why I’ve stuck with Claude as the LLM I choose to pay for a few months at a time. It has an uncanny sense of style that ChatGPT entirely fails to capture. I found Claude’s article entirely believable and legitimately funny. It addresses my complaints from two years ago—it attributes quotes to individuals rather than nameless people with a title, and doesn’t hit us over the head with any of the jokes. It plays it straight, shares the story, and makes us laugh.

ChatGPT has slightly refined itself but still suffers from being too on the nose with its humor. SunnyBot-9000 is obviously an optimistic robot. That’s a case of nominative determinism if I’ve ever seen it. Compare that to Claude’s creation of IRIS-7, where the running gag is that nobody understands how this bot’s mien came to be. ChatGPT also leans heavily into LLMs’ potential inaccuracies, making it feel like it was written two years ago. Hallucinations still occur, I’m sure, but it’s not what it was upon release. Claude focuses on the tasks’ relative drudgery, which I find more compelling. The happy idiot of ChatGPT’s creation could be refined, but on a first pass, it’s rather dull.

Interestingly, they both used the same rough setup about deleting/resetting the LLM, which it then took in stride. While the punchlines were different, they both landed.

I talked about the characteristic ending of articles from The Onion in my post two years ago, and ChatGPT failed spectacularly yet again. It at least puts the sentiment in a direct quote from the bot, similar to Claude, but hoo-boy, is it objectively not a funny ending. It has the trappings of something that could be funny, but there’s no flair or subversion of expectations. It keeps pounding the same nail of “Live, Laugh, Love” with no unique edge.

ChatGPT has certainly improved compared to two years ago, but it’s impressive what Claude was able to churn out. Heck, Claude even got the rough formatting of “CAPITALIZED CITY NAME—” that begins every Onion article. ChatGPT couldn’t be bothered.

Posted on

Two Good Essays

These are two essays by a couple of “guys on the Internet” whose work I enjoy. John Gruber created Markdown and now works in the Apple/tech media space. Merlin Mann used to be Merlin Mann, one of the first modern productivity gurus. Now, he’s essentially a comedic personality. Both are tremendous writers, and these two essays are supremely affecting and have unique styles that show the authors flexing their muscles.

Cranking by Merlin Mann, posted April 22, 2011. (About parenting and priorities.)

How It Went by John Gruber, posted November 8, 2024. (About the election, kind of.)