I’m undertaking a year-long crash course in the humanities. These are my notes for week 3. Following Ted Gioia’s curriculum, this week I read the remainder of the Odyssey. On the audiovisual front, I watched a movie that made me think differently about the poem’s subject. Readings Last week included books 1-10 of the Odyssey. This week I “read” through the remainder of the poem. “Read” is in quotes because I mostly listened to the audiobook I mentioned last week. The story pivots when Odysseus returns to Ithaca. Surprisingly, it happens halfway through the poem: all of the famous “adventure” stories, including the encounter with the cyclops and the sirens, happen early on. The second half emphasizes social relations and (especially) loyalty. When Odysseus returns home, Athena disguises him so he can observe his compatriots. He wants to learn who’s remained true to him and who’s gone over to the suitors who are courting his wife and consuming his wealth. Notably, he tests Penelope, his wife. He consults primarily with two male confidants: his son Telemachus and Eumaeus, his chief swineherd. The story takes surprisingly long to resolve, which it does in a series of astonishingly violent vignettes. An epilogue reminds us this return is only a brief respite: Odysseus is destined to continue wandering. A key theme: the expectations and responsibilities imposed by family ties and social roles. Odysseus is king and expected to behave as such. Hosts behave in proscribed ways toward guests. Parties who violate norms face consequences. In particular, we’re continually reminded of parents’ expectations (especially fathers’) expectations toward their children and vice-versa. Audiovisual Music: Gioia recommended Beethoven’s third, fifth, and ninth symphonies. These are all works I know well. Still, I revisited the third symphony and fifth symphonies. Art: Gioia recommended looking at Greek architecture. As with sculpture, architecture is hard to appreciate on screens. I’ve visited the Parthenon IRL, but did it without a guide. As a result, I missed a lot. This lecture from a professor at Notre Dame’s school of architecture filled in blanks: A friend of mine studied architecture at Notre Dame, and I was always surprised at that school’s focus on classicism. I didn’t understand the relevance of aping ancient architecture in modern times. I still don’t. That said, I can appreciate aspiring to manifest idealized forms in an “imperfect” world. Cinema: I asked ChatGPT for recommendations of films inspired by the Odyssey. A few were obvious (e.g., 2001: A SPACE ODYSSEY, adaptations of the Odyssey itself) but one stood out since it was already on my to-watch list: Wim Wender’s PARIS: TEXAS. Like the Odyssey, this film follows a man’s journey “home.” In this case, the journey is internal. The protagonist, Travis, is wandering lost and mute in a barren landscape. He seeks to put the pieces of his shattered family back together. Reflections PARIS: TEXAS raises important questions: What is a father? What responsibilities do fathers have towards their children? How should adult men behave? How should they relate to their own parents’ legacy? These questions are relevant today, but they were urgent in 1984 when the movie came out. The social revolutions of the 1960s upended traditional roles. As often happens, naive idealism led to disaster. Travis’s generation wandered into middle age without a compass. The result: shattered families and loneliness. The Odyssey portrays a radically different milieu. The relationship between Telemachus and Odysseus (and Odysseus and Laertes, for that matter) couldn’t be more different than that of Travis and Hunter. Characters in the Odyssey don’t shirk or even doubt filial or social duties – they celebrate them. To be clear: those structures have problems. The Odyssey takes horrific violence – including violence against women – for granted. Social roles are unfair and inflexible. People and animals are objectified. “Fate” overrides choice – and is often used as an excuse for atrocities. A verse from the Rush song Freewill kept coming to mind as I read the poem: A planet of playthings Of course, we shouldn’t abide by Bronze Age values. Nobody reads the Odyssey today looking for explicit instructions on how live. (Unlike the Bible – more on that later in this course.) Still, the stories we tell ourselves about who we are matter. They offer pointers for leading fulfilling lives. That’s how I’m approaching these ancient texts. Stories that stand the test of time do so because they connect us to deep truths. The classics are relevant to the degree they help us answer enduring questions. The one I considered this week was one Travis asked in the movie: What does a father look like? We won’t get direct answers from these stories. The best they can do is sketch ideals. Much like the proportions in Greek architecture, we must adapt ideals to the conditions we meet on the ground. Which is to say, cultures need models. For 27 centuries, Odysseus was a preeminent model for adult masculinity in Western culture – flaws and all. We’ve moved on, thankfully. Alas, the fictional character most likely serving that role today is Homer Simpson: a selfish dolt driven by his id. I’ll take the other Homer any time.

LLMs are a general-purpose technology with seemingly endless use cases. Among my favorite is unlocking the potential of other technologies. For example, all modern “desktop” OSs come with shell environments. If you know a bit of scripting, you can automate tasks in ways that go beyond what you can do in the default WIMP UI. But “know a bit of scripting” is a tall ask. Command line shells harken to an earlier era of computing when the usability/power balance skewed toward power. Learning shell scripting is hard and it’s easy to make catastrophic mistakes. That’s where AI comes in. LLMs “know” a lot more about esoteric computing environments than you. If you know enough to know what shell scripts are, how they work, and what they can do for you, you can ask LLMs to write scripts for you. They likely won’t be perfect at first, but you’ll have a starting point – and learn in the process. Note that in this scenario, the LLM doesn’t provide net new functionality. Instead, it unlocks latent potential in your existing stack. Shell scripting is decades old. But if you’ve never used it, it’s new to you. And LLMs know more about older stuff than newer stuff. The more established the technology, the more reliable the results. Case in point: yesterday, I had an astonishingly helpful interaction with ChatGPT. Here’s the scenario. This week, I kicked off a new client engagement. As usual, I’m sifting through lots of research materials. Here’s what I was trying to do. I have two text documents with long outlines of bullet points documenting user personas. Each bullet point has the following format: Headline of the item: A longer description that explains what the item is about, including examples and such. Like I said, there were lots of these bullet points structured in categories (a branch for a set of points.) I wanted to make sense of them: find patterns, high-level groupings, etc. I’d prefer to turn them into “stickies” in a canvas where I can cluster them and such. My favorite way of doing this is using Tinderbox, a hypertext note-taking tool that lets you explore textual data. I don’t blame you if you’ve never heard of it: even though it’s been around for a long time, it’s a niche product. It’s also complex and has a steep learning curve. I wanted to import the text into Tinderbox notes, one note per bullet. I wanted the text before the colon (e.g., “This is a summary of the item”) to be the note’s title and the text following the colon should the note’s body. Tinderbox can easily import texts and break them up at arbitrary delimiters. But there were two problems with the default approach: If I used paragraph breaks as the delimiter, the entire bullet text would become the title. If I used the colon as the delimiter, then the stuff to the left of the colon would become one note and the stuff after the colon another note. Neither was what I wanted. I opted to import the whole note using paragraph breaks and then clean up the resulting titles by dropping everything after the colon. The obvious problem: doing this manually is time-consuming. Fortunately, Tinderbox provides several ways of automating tasks. It has at least one proprietary scripting language. There’s good documentation, but because Tinderbox is a niche product, it’s hard to find examples of the exact thing you’re trying to do. I’ve spent hundreds of hours trying to solve these kinds of problems. I know the tool can do what I want, but don’t know what magical incantation unlocks the functionality. So I peruse documentation and Substack and try one thing after another until I hit something that works. It’s frustrating. This is exactly the kind of scenario where LLMs help. So I opened ChatGPT and typed: ME: Are you familiar with Eastgate’s Tinderbox? CHATGPT: Yes, I’m familiar with Eastgate’s Tinderbox. It’s a sophisticated tool for note-taking, personal knowledge management, and idea visualization. Tinderbox allows users to create, organize, and analyze notes in various formats, including maps, outlines, and timelines. It’s especially useful for writers, researchers, and thinkers who want to explore complex ideas and connections. Some key features of Tinderbox include: Dynamic Notes: Notes can include metadata, links, and scripts to automate processes. Visualization: Multiple ways to view and interact with your notes, like maps, outlines, and attribute-based dashboards. Prototyping: Templates and rules to create dynamic relationships between notes. Export: Flexible exporting options for sharing or integrating with other tools. Customizability: Users can tailor the interface and behavior to their specific workflows. If you’re using it or considering it for your projects, let me know–I’d be happy to help brainstorm ways to make the most of it! I started here because I wanted to validate we were talking about the same tool. There might be other applications named Tinderbox; I wanted to set the right context from the start. ChatGPT’s answer gave me confidence that we were in the right neighborhood. With that out of the way, the next step was asking ChatGPT for help with my specific need. When doing this, I try to be as specific as possible. In this case, I knew Tinderbox has a feature called stamps that lets you automatically run scripts on notes. It’s the right approach for this problem; I just needed help with the script itself. So this is what I typed: ME: Please help me create a stamp for Tinderbox. I want to make a little script that truncates a note title at a delimiter (:), losing the second half of the title. Does this explanation make sense? Note that I’m asking for confirmation that my instructions make sense. ChatGPT acknowledges that it does and gives me confirmation by explaining what it knows about stamps. Again, this builds my confidence in the proposed solution: CHATGPT: Yes, that makes perfect sense! A stamp in Tinderbox is essentially a small script that you can apply to notes for specific actions. Here’s a script for your desired functionality: Stamp Script $Name = $Name.split(":")[0]; Explanation: $Name: Refers to the note’s title in Tinderbox. .split(“:”): Splits the note’s title into an array using the colon (:) as the delimiter. $Name =: Assigns this truncated value back to the note’s title. Steps to Create the Stamp: Open Tinderbox and go to the Stamps menu. Select Edit Stamps…. In the Stamps editor, create a new stamp and name it (e.g., “Truncate Title at Colon”). Paste the script above into the script area for the stamp. Click OK to save. Now, you can apply this stamp to any note, and it will truncate the title at the first colon, discarding everything after it. Let me know if you need further clarification! I followed these instructions and applied the stamp to my notes. It worked on the first try. Now, let’s unpack what’s happened here. First, a task that would’ve taken me several hours took a few minutes. That’s great. But second, and perhaps more importantly, ChatGPT’s answer is helpfully annotated. The explanation, in particular, concisely unpacks the script to tell me what it’s doing. This doesn’t just build my confidence in the answer, it also teaches me stamp scripting. An analogy: I’m convinced using Grammarly for a few years made me a better writer. Yes, it’s great that it corrected my writing. But that wasn’t the only benefit. Seeing the same error come up time after time made me realize how my writing fell short – in a context where I could do something about it. LLMs do the same thing but for… everything. English is a damned powerful API! Frankly, I was blown away that this worked in the first try. Tinderbox is a not a mainstream application, Obviously, this includes venerable – yet esoteric – tools like Tinderbox and sed. I’ll never be a Tinderbox master. But I know enough to know what to ask for – and LLMs are there to provide it. I saved enough time in this fifteen-minute interaction to pay for an entire year of ChatGPT Plus.

Update: in the afternoon of January 14, news emerged that Sonos CPO Maxime Bouvat-Merlin is also leaving the company. Sonos CEO Patrick Spence is out, felled by last year’s disastrous app launch. I have no inside track on what happened, but from what I’ve read, Sonos’s leaders made some terrible decisions. They’re worth looking at so we can avoid making similar mistakes. Before I elaborate, a few disclaimers. I’m not a Sonos customer. I’ve heard good things about their products and bad things about their business practices. (They eventually rescinded some.) I don’t know anyone who works there and have no details on how they went about this project. So this post is speculative. That said, news reports make it clear that Sonos made several questionable choices. From my vantage point, the most egregious was deciding to wholly scrap their previous app under pressure. Scrapping the old app may be excusable, since it had accrued a lot of technical debt. In September, Bloomberg published an article by David Lee that offers insights into what happened. Among other things, it highlights the following: For two decades, Sonos had allowed its tech debt to pile high. When it undertook in earnest its effort to revamp its app in mid-2022, the company knew it was sitting on infrastructure and code written in languages that were pretty much obsolete. The Sonos app had been adapted and spliced and tinkered with so often, the vast majority of work being performed for the new app was less about introducing new functionality than sorting out the existing mess. I bet the codebase was an unmanageable hairball. So I can understand the impulse to retire it. The problem is that Sonos isn’t a product; it’s an ecosystem. And ecosystems evolve gradually. When the company introduces new products, developers tweak the codebase. They introduce exceptions to make the new product work alongside older products. It’s not just features: developers also establish protocols and standards. When things break, they fix them. Do this repeatedly over two decades and you end up with a complex system that works – even if it’s held together with tacky tape and prayers. This takes time. You can’t quickly recreate the complexity embodied in twenty years’ worth of tweaks. By “works,” I mean offers customers a good experience. Customers don’t care if the codebase is a giant hairball. They care if their expensive new speaker gets arbitrarily dropped from the network. As I see it, Sonos failed to heed Gall’s law: A complex system that works is invariably found to have evolved from a simple system that worked. A complex system designed from scratch never works and cannot be patched up to make it work. You have to start over with a working simple system. The old app was a complex system that worked, at least from the user’s perspective. One must be very careful when messing around with such things. You can’t scrap an ecosystem without pissing off a lot of people. But Sonos wasn’t careful. Fixing the hairball was a daunting task, so they didn’t prioritize it. To get around this, they hitched it to a critical new product launch. Again, Lee: The company could have tackled its tech debt sooner but appears to have lacked a crucial element: urgency. It finally came in the form of the Sonos Ace headphones, the first product in the Sonos range to be fully mobile rather than using home or office Wi-Fi. The app needed to be rebuilt, as did the cloud computing setup underpinning it. This was happening amidst 1) layoffs and 2) a reorg. 🤔 These are leadership decisions. To recap, they opted to: Scrap their old app and restart from scratch Tie the new app to a critical product launch Do it while implementing major organizational changes Each of these decisions is questionable on its own. In combination, they proved disastrous. Lesson: be conservative when changing established ecosystems. Systems that have evolved over time are better fit to their purposes than anything you can design from scratch – even if the team is exclusively composed of brilliant designers and engineers. With a complex enough system, nobody can account for all eventualities. The company acknowledged as much in their postmortem. Again, this is from the Bloomberg story: [Sonos lead counsel Eddie] Lazarus said the company had a list of what were regarded as “essential” bugs that needed to be fixed before launch. Bugs it deemed to be less critical, or functionality it felt could be left off temporarily, would be dealt with after the launch. When I asked if it was possible the company’s idea of an “essential” bug might have differed from what customers considered vital functionality, Lazarus paused before saying: “Our list of essential bugs, obviously, was not comprehensive enough.” “Our list of essential bugs was not comprehensive enough” is a phrase for the ages. It perfectly captures the risk of violating Gall’s law.

I’m excited to share with you a new podcast: Traction Heroes. The first episode is now up on the major podcasting platforms. You can also see show notes and get the RSS feed at www.tractionheroes.com. Here’s the backstory. My previous podcast, The Informed Life, originated as a way to do research for my book Duly Noted. That book launched a year ago. After the initial marketing wave played out, the show had served its purpose. I enjoy podcasting, but my consulting work focuses on more strategic issues. So I started thinking about doing a show with a different focus. I also wanted a different format: rather than interviews, I wanted a running conversation with a co-host. When thinking about who this might be, one name popped to mind: Harry Max. Harry is one of my oldest friends in the IA community. His career has focused more on management than mine, so we’re a good mix. We’re also Rosenfeld Media stablemates: his book Managing Priorities came out last year. He was my guest in TIL Episode 143 and I noted our chemistry. Which is to say, Harry was my ideal choice for a co-host. I emailed him to see if he’d be game. To my delight, he agreed to give it a shot. Over dinner last year, he suggested a format that got me excited. I’m not gonna tell you what that is; you’ll have to listen to find out. If you do, I’d love to hear what you think – please get in touch with comments or ideas for possible topics. Onward!