More from Jorge Arango
Week 7 of my humanities crash course had me exploring ancient Mesopotamia with a side trip to northern India. I also watched an Iranian film that had me pondering the meaning of life. Readings This week, I read two short ancient texts: the Epic of Gilgamesh and the Dhammapada. Let’s tackle them in order. I’d never read any ancient Mesopotamian literature, so this was all new to me: the pantheon, story, style, etc. were thrillingly unfamiliar. Gilgamesh is around 1,500 years older than Homer, and it shows: there are lots of repetitive passages and what felt like archaic writing. But human nature hasn’t changed much in 4,700 years. People still love, hate, drink, eat, etc. – and they still fear death. Gilgamesh is the awe-inspiring, despotic king of Uruk. The gods answer his beleaguered subjects’ prayers in the form of Enkidu, a rival who becomes Gilgamesh’s friend. They embark on several heroic exploits and end up pissing off the gods. As a result, they condemn Enkidu to death. Despondent and fearing for his own death, Gilgamesh goes in search of the secret of immortality. His travels take him to Utnapishtim, immortal survivor of the great flood. Our hero finds a plant that restores youth, but loses it. By the end of the story, he accepts his fate as a mortal. The story moves fast and is surprisingly engaging. It includes early versions of ideas that would resurface later in the Bible. (Most obviously, Noah and the flood.) There’s also some material that probably wouldn’t pass muster in our prudish time. The Dhammapada is one of the central Buddhist scriptures. I was familiar with several of these texts but hadn’t read the whole thing. Gioa notes that he recommended it because of its length, but there are also obvious connections with Gilgamesh. For example, several verses in the Dhammapada deal with attachment. For example, here’s verse 215: From affection comes grief; Gilgamesh suffers from such an attachment. Here’s the moment of Enkidu’s death: He touched his heart but it did not beat, nor did he lift his eyes again. When Gilgamesh touched his heart it did not beat. So Gilgamesh laid a veil, as one veils the bride, over his friend. He began to rage like a lion, like a lioness robbed of her whelps. This way and that he paced round the bed, he tore out his hair and strewed it around. He dragged off his splendid robes and flung them down as though they were abominations. He wishes to hold on: Then Gilgamesh issued a proclamation through the land, he summoned them all, the coppersmiths, the goldsmiths, the stone-workers, and commanded them, ‘Make a statue of my friend.’ The statue was fashioned with a great weight of lapis lazuli for the breast and of gold for the body. A table of hard-wood was set out, and on it a bowl of carnelian filled with honey, and a bowl of lapis lazuli filled with butter. These he exposed and offered to the Sun; and weeping he went away. You can probably relate if you’ve ever lost someone dear. Human nature. Audiovisual Gioia recommended Stravinsky’s Rite of Spring and Wagner’s Overtures. I’m very familiar with both so I didn’t spend much time with either this week. For a new take on one of these familiar classics, check out Fazil Say’s astonishing piano version of the Rite of Spring. Here’s a short portion: Gioia also recommended looking at ancient Mesopotamian art. I didn’t spend as much time on this as I would’ve liked. That said, this introductory lecture provided context while highlighting major works of art and architecture: I took a different approach to cinema this week. Rather than go by an AI recommendation, I went down the old-fashioned route. (I.e., Google.) Specifically, I thought this would be a good opportunity to check out Iranian cinema. I’ve heard good things about Iranian films, but had never seen one. Googling led me to this article on Vulture. After reading through the list, I picked Abbas Kiarostami’s TASTE OF CHERRY. Yet again, I’ve gravitated towards a film about a middle-aged man in despair. (Is the Universe trying to tell me something?) Kiarostami effectively uses a minimalist style to explore what makes life meaningful despite (or perhaps because) of its finitude. Reflections There’s a pattern here. This week’s works dealt with core issues people have grappled with since we became people. The big one: how do we deal with death? Not just the impending death of everyone we love, but our own. Gilgamesh offers the traditional “Western” answer: “I can’t even.” So, fight it! He looks for a MacGuffin that’ll let him go on living and perhaps brings his loved ones back. It’s an idea that has had many progeny in our mythologies. And it’s not just the stuff of fiction: the impulse is still alive and well. (Pardon the pun.) The Buddha offers a different approach: non-attachment. It’ll be easier to let go if you don’t become enmeshed with things, people, and your own sense of being. So you train your mind so it won’t hang on. (Even the idea of “your mind” is suspect.) The price: not feeling either extreme. No despair, no elation. Kiarostami’s film suggests a third approach: accepting the inevitability of death while reveling in the experience of being alive. (You could argue this is part of the Buddhist way as well.) I won’t say more in case you haven’t seen TASTE OF CHERRY, but suffice it to say the film employs a clever structural trick to wake you from your slumber. Grappling with these kinds of issues is the point of studying the humanities. Yes, I know you’re busy. I’m busy too. But some day, the busyness will stop – as will everything else. I’m committed to living an examined life, and that requires thinking about stuff we’d rather put aside so we can get on with the next Zoom meeting. Notes on Note-taking I’m also committed to the other point of this humanities project: learning how to learn better in this AI age. This week, I continued tweaking my note-taking approach. I took notes in the Drafts app as I read, building an outline as I go through the week. I wrote down the main points I learned and things I’d like to share with you. I then elaborated this outline on one of my morning walks. My mind works better when my body is moving and clear from the day’s detritus. I also tweaked my note taking approach around the readings. I had an LLM summarize the reading and then used that as a refresher to write a summary in my own words. I’ve done the same in previous weeks. What’s different now is that I then pasted my summary into a ChatGPT window with a simple prompt: I read The Epic of Gilgamesh. What is wrong with this description of the story?: Gilgamesh is king of Uruk. He’s described as the strongest and most beautiful man in the world. He’s also something of a despot. He befriends Enkidu, a wild man who is almost as strong as Gilgamesh. They go on several adventures, which entail opposing the wishes of one of the Mesopotamian deities. Eventually, the gods are angered and decree Enkidu must die. Grief-stricken, Gilgamesh goes in search for the secret of eternal life, only to learn that human lives are limited. He returns to lead his people with this newfound wisdom. The LLM offered a helpful response that clarified nuances I’d missed: Gilgamesh wasn’t “something of a despot”; he was a tyrant. The gods created Enkidu as a counterbalance to answer his subjects’ calls for relief. The taming and channeling of this force of nature through initiation into human pleasures is an important aspect of the story I’d left out. Details about Gilgamesh and Enkidu’s transgressions against the gods. (These seemed less relevant for a high-level summary.) The fact Gilgamesh isn’t just searching for immortality because he’s grief-stricken over Enkidu’s death; he’s also fearing for his own life. The end of my summary was wrong; the book doesn’t suggest Gilgamesh changed as a result of his experiences. This last point is important. In writing my summary, I made stuff up that wasn’t in the book. I attribute my error to the fact I expect closure from my stories. Gilgamesh precedes Aristotle’s Poetics; its authors were under no compulsion to offer the hero a redemption arc. Which is to say, humans hallucinate too – and LLMs can correct us. Up Next Next week, we’re reading ancient Egyptian literature. I couldn’t find an ebook of the text suggested by Gioia, so I’m going with another Penguin book, Writings from Ancient Egypt. I studied some Egyptian architecture in college, and look forward to revisiting this part of the world and its history. Check out Gioia’s post for the full syllabus. I’ve started a YouTube playlist to bookmark all the videos I’m sharing in this course. And as a reminder, I’m also sharing these posts via Substack if you’d like to subscribe and comment.
Today is Peter Gabriel’s 75th birthday. He’s contributed much through his music and by bringing people together through the arts. But today, I want to celebrate one of his songs that’s had a profound impact on my life: Solsbury Hill. Solsbury Hill was Gabriel’s debut single as a solo artist. That’s significant because of what the song is about. Before this, Gabriel was the lead singer of prog rock band Genesis. He left the band at a peak in their artistic and commercial development. They were highly regarded. So it was a risky move. But his personal and professional development demanded that he strike out on his own. And that’s the subject of Solsbury Hill: the scary and exciting moment when you’ve decided that further development requires you to move on, and you’ve taken decisive steps to do so. It’s scary because you’ll let people down. They’ve come to depend on you in your current guise. Now, you won’t be there anymore. It’s also scary because you’re leaving a known (and therefore, “safe”) situation to face uncertainty and doubt. What if the solo record doesn’t chart? What if people don’t turn out for the show? What if I can’t produce at the same level without my bandmates? Imposter syndrome affects even the highest performers. But the shift is also exciting. The new context allows more freedom: you don’t have to run decisions past bandmates anymore. You can also build on the experience and potential you’ve gathered so far and take it to the next level, leaving behind the baggage. The future is open. You can see far into the distance, as you would atop a hill on a clear day. And you can see what you’re leaving behind. As Gabriel put it, the song is about “being prepared to lose what you have for what you might get … It’s about letting go.” There are rare moments in life when you can choose a different path. They’re often not the perfect moment. (That’s why it’s scary!) But deep down you know you’ll regret letting it pass. Solsbury Hill doesn’t celebrate success. Gabriel wasn’t yet a successful solo artist when he recorded it. Instead, it celebrates the elation you feel after getting on the new path. Of having the courage and conviction to calmly say, “it’s time to move on” – and then doing it. I did not believe the information – Peter Gabriel, Solsbury Hill
Co-Intelligence: Living and Working with AI by Ethan Mollick Portfolio, 2024 Over the weekend, I caught up with a friend I hadn’t seen in years. When I explained that most of my work these days is focused on AI, he asked if there was one book he could read to understand how to better use AI. This is the book I recommended. Why? Because it offers a clear explanation of how the technology works, thoughtful explorations of what it means for us, and practical suggestions for using it to help with common tasks. AI isn’t like other technologies. As Mollick puts it, We have invented technologies, from axes to helicopters, that boost our physical capabilities; and others, like spreadsheets, that automate complex tasks; but we have never built a generally applicable technology that can boost our intelligence. The book is divided into two parts. The first explains the fundamentals, including how transformers work and the challenges inherent in aligning AI goals with human goals. Mollick lays out four principles for working effectively with AI: Always invite it to the table: AI is a general-purpose technology; it behooves you to try it for different ends. Be the human in the loop: assume AI will need supervision and guidance; provide it. Treat AI like a person, but tell it what kind of person it is: don’t fall into the trap of anthropomorphizing AI – but it’s helpful to suspend your disbelief. Assume this is the worst AI you’ll ever use: the technology is improving fast; assume the things that are difficult or impossible today will be doable in the future. The second part explains how to use AI effectively by seeing it through the lens of five possible roles: As person: even though we should remember AIs aren’t people, it can be useful to ask it to simulate human attributes such as personality and particular expertise. As creative: AI can assist us in our creative efforts or replace our creative functions outright. You’ll be better served by using AI for creative augmentation rather than replacement. As coworker: AIs can handle information tasks at much greater speed and scale than people. Knowing what they can and can’t do well can help you get the most out of them in a work context. As tutor: AIs can offer personalized instruction and draw from a larger corpus than what any human can. That said, they can also hallucinate. As coach: AIs can help us find patterns in data and help nudge us towards accomplishing our goals. In all five cases, the emphasis is on collaborating with AI as a partner rather than a replacement. The book offers concrete examples of prompts and the subsequent responses. Some are about the writing of the book itself, a nice meta-touch. The last chapter speculates about four possible futures, ranging from a scenario where the technology stalls to the opposite extreme where AI becomes all-powerful. The middle scenarios – slow growth and exponential growth – seem likeliest to me. As I implied above, this is the best primer I’ve found on what most people currently understand by AI. The book is clear about the risks and challenges inherent in the technology, but also practical, informative, and philosophical. Much of its advice validates my experiences with the technology. Co-Intelligence: Living and Working With AI
In episode 3 of the Traction Heroes podcast, Harry and I discussed the relationship between decision-making and data. Is it ok for some decisions to be made intuitively? What role do emotions play in decision-making? How do you deal with stakeholders who demand that decisions be backed with data? Tune in to find out!
Week 6 of my humanities crash course included four books from Herodotus’s Histories and Plato’s Symposium. I also listened to gorgeous music from exotic (to me) ports of call, learned about Persian art and architecture, and watched a new documentary about René Girard. Readings For this week’s readings, Gioia contrasted writings about love and war. First up, Plato’s Symposium. Socrates and his buddies gather for a rowdy banquet. They drink lots of wine and take turns giving speeches about love. (Eros.) The most interesting is Aristophanes’s mythological yarn about the origins of the genders. The speeches cover romantic or sexual love, not the kind of brotherly love (agape) found in the Christian scriptures. That’s a later development in our history. Herodotus’s Histories strikes a completely different tone. It details the origins and events of the Greco-Persian Wars of the 5th Century BCE. I’d read this book over two decades ago, and loved it. Per Gioia’s recommendation, I only re-read four books (chapters) this time. Book 1 offers background on the conflict, starting with inter-tribal raids and leading to the rise of the Persian Empire under Cyrus the Great. Book 6 details the early stages of the war. The Persians push into Greece, leading to the battle of Marathon, where Athenians defeat the Persians. In book 7, a huge Persian army under Xerxes’s command builds a bridge over the Hellespont and marches into Europe. Despite superior numbers, they’re held back at Thermopylae, where a small Greek force makes a valiant (if ultimately futile) stand. Book 8 focuses on naval battles. The Persians take Athens, but Greek forces defeat them at the pivotal battle of Salamis. Xerxes decides to return home, deputizing someone else to finish the war for him. The Histories is famous as the first literary work recognizable as history. It isn’t easy reading (there are many unfamiliar names) but Herodotus provides lots of color and what we might call “human” interest – although in this work, it’s often ghoulish. (More on this below.) Audiovisual Gioia recommended several compilations from the Nonesuch Explorer Series. I own one of these on CD, but hadn’t realized they were available in Apple Music. The Bali and Iranian collections are standouts. Discovering these albums in streaming format has already made this Humanities Crash Course worthwhile. They’re that good. Gioia also recommended looking at Persian art and architecture – appropriate given the role of that civilization in the Histories. This video was insightful and entertaining: Cinema: Although it’s not a classic film, I planned to watch Zack Snyder’s 300, which based on the events in the Histories. My son has been nudging me to watch it with him. (He’s already seen it.) Alas, we couldn’t make it happen – so I’m going to wait until we can watch together. Rather than seek out another classic film, I watched the new documentary about René Girard. It’s on YouTube: I haven’t read Girard, but I’ve read about Girard. Since watching the documentary, I bought Things Hidden Since the Beginning of the World, which I plan to read this year. Reflections Girard’s central claim is that much human behavior – particularly conflict – can be explained by our drive to imitate others. Conflict results from two people wanting the same thing. Societies avoid mass destruction by focusing the conflict on a sacrificial scapegoat. These patterns are evident in both the Symposium and the Histories. Alcibiades’s desire for Socrates is explicitly driven by imitation. Conversely, Socrates’s conception of love points away from individual desire toward abstraction. I don’t know enough yet about Girard’s work to offer a deeper analysis. That said, the Histories also seemed filled with Girardian mechanisms. Not only does it explicitly deal with conflict, but actors often resort to murderous scapegoating. Some of these sacrifices are shockingly brutal. I won’t get into details here, but suffice it to say human societies have progressed since Herodotus’s time. And that was my biggest lesson I took from re-visiting this work. One reason for reading the classics is that you can clearly see the arc of the moral universe bending towards justice. People today don’t resolve conflicts by slaughtering others’ innocent family members. For Herodotus, the most horrific murders seem like business as usual. I read this as my people were melting down in social media over the latest political outrage. Yes, much of what is happening today feels unprecedented, but that may be because we have such short memories. I couldn’t help but think, “these people don’t know how good they have it.” Reading books like the Histories brings perspective. And of course, despite all those advances, people today still demonstrate hubris, overconfidence, imperialistic and totalitarian drives, etc. Plus ça change. Notes on Note-taking I expanded my Obsidian note for the Dialogues to include the Symposium. I used the Text Generator plugin to create summaries of the work, which refreshed my memory as I reflected on what I’d read. (I usually take these literature notes a few days after finishing the text, to give it time to simmer in my mind.) I didn’t yet have a note in my vault for the Histories; my previous reading happened before I started taking disciplined notes. I started a new note now, but only focused on the parts I read this time. I may revisit the work in the future and fill out the rest. Taking a page from last week’s experience, I used ChatGPT to help me understand the books of the Histories. Before starting each book, I asked for a succinct summary. I also asked the AI to tell me what to look for and how the work might be relevant to someone reading today. Here’s an example of one such response (with emphasis in the original): Here is a summary of Book 7 of Herodotus’s Histories, often titled “Polymnia.” This book primarily focuses on Xerxes I’s invasion of Greece and the events leading to the famous battles of Thermopylae and Artemisium. I. Xerxes Prepares for Invasion (7.1-55) Darius I dies, and his son Xerxes I ascends the throne. After some hesitation, Xerxes decides to avenge the Persian defeat at Marathon by launching a full-scale invasion of Greece. Xerxes gathers a massive army and navy, with contingents from across the Persian Empire, reflecting the vastness of his domain. A grand engineering project is undertaken to build a canal at Mount Athos and bridges over the Hellespont to facilitate the Persian advance. II. Debate and Motivation for War (7.8-19) Xerxes is influenced by his advisors, particularly Mardonius, who advocates for expansion into Greece. Demaratus, the exiled Spartan king now serving Xerxes, warns him of the Greeks’ determination and fighting spirit, especially that of the Spartans. III. The Persian March to Greece (7.56-137) Herodotus provides detailed descriptions of the Persian army and its preparations, emphasizing its vast size and the logistical challenges it faces. The Persians cross the Hellespont using a pontoon bridge and begin their march through Thrace and Macedonia, forcing local tribes to submit. IV. Greek Preparations and Disunity (7.138-174) The Greek city-states are divided over how to respond to the Persian threat. Athens and Sparta take the lead in organizing a coalition to resist Xerxes. A plan is developed to block the Persian advance at Thermopylae, a narrow mountain pass, and Artemisium, a strategic naval chokepoint. V. The Battle of Thermopylae (7.175-239) King Leonidas of Sparta leads a small force of 300 Spartans and a few thousand allied Greeks to defend Thermopylae. Despite being vastly outnumbered, the Greeks hold off the Persian army for several days, using the narrow terrain to their advantage. Ultimately, the Persians discover a mountain path that allows them to outflank the Greek defenders, thanks to the betrayal of Ephialtes. Leonidas and his men make a heroic last stand, becoming legendary symbols of courage and sacrifice. VI. The Persian Advance After Thermopylae (7.240-end) With Thermopylae secured, the Persian army pushes further into Greece. The book sets the stage for further confrontations, including the pivotal Battle of Salamis, which will be described in Book 8. Key Themes in Book 7 1. Hubris and Fate: Xerxes’s vast ambition and his dismissal of warnings about Greek resilience highlight the theme of hubris (excessive pride) and its eventual consequences. Herodotus hints at the role of fate, suggesting that the Persian invasion is destined to fail despite its overwhelming force. 2. Heroism and Self-Sacrifice: The story of Leonidas and the Spartans at Thermopylae embodies Greek ideals of heroism, honor, and sacrifice for the greater good. This stand becomes a key moment in Greek collective memory and identity. 3. East vs. West: Herodotus emphasizes the contrast between Persian autocracy and Greek freedom, a recurring theme in the Histories. The Persian army’s size and complexity symbolize imperial power, while the Greeks’ smaller, more united force represents their commitment to liberty. 4. Cultural Observations: Herodotus continues his ethnographic approach, providing detailed descriptions of Persian customs, military practices, and engineering feats. What to Look For The Role of Leadership: Compare the leadership styles of Xerxes and Leonidas. How do their choices reflect broader cultural values? The Importance of Geography: Pay attention to how geography shapes the conflict. Thermopylae and Artemisium are strategically chosen to offset Persian numerical superiority. Foreshadowing of Persian Defeat: Notice how Herodotus subtly foreshadows the ultimate failure of the Persian invasion through omens, warnings, and the theme of overreach. This overview should help guide your reading of Book 7. Let me know if you’d like more details on any particular section or theme! Although this was a risky approach (I hadn’t yet read the text so I couldn’t tell whether the AI was hallucinating,) I found the summary insightful. Seeing the outline of the work helped me sift out the signal (main narrative) from the noise (all those confusing names and genealogies.) I’m going to do this with other readings in this course. I also asked ChatGPT about the presence of Girardian concepts in both the Symposium and the Histories. Doing so helped me understand all three better. Again, I’m just getting started with Girard, so I don’t know whether ChatGPT is misleading me. That said, I still found it helpful for thinking about these ideas. Up Next I’m reading the Epic of Gilgamesh and the Dhammapada for next week. Neither was available in Standard Ebooks, so I’ve purchased the Penguin Kindle editions. (I’ve had good success with Penguin ebooks so far in this course.) Check out Gioia’s post for the full syllabus. As a reminder, I’ve started a Substack to share what I’m learning in this course. Head over there if you want to subscribe and comment.
More in technology
An update to my app, Quick Reviews, is rolling out now! After a lot of feature adds in the first few updates, I took this as a chance to clean up some bugs and improve a few elements that made the app a little annoying to use at times. Oh,
The age-old combination of physical locks and keys, although reliable, also comes with a few drawbacks, such as when you lose the key or you want to share access with someone else remotely. Davide Gomba has recognized this and built the MKR Keylock project as a way to address some of these shortcomings. Starting with an existing electronic […] The post MKR Keylock is an open-source IoT keypad for your front door appeared first on Arduino Blog.
Week 7 of my humanities crash course had me exploring ancient Mesopotamia with a side trip to northern India. I also watched an Iranian film that had me pondering the meaning of life. Readings This week, I read two short ancient texts: the Epic of Gilgamesh and the Dhammapada. Let’s tackle them in order. I’d never read any ancient Mesopotamian literature, so this was all new to me: the pantheon, story, style, etc. were thrillingly unfamiliar. Gilgamesh is around 1,500 years older than Homer, and it shows: there are lots of repetitive passages and what felt like archaic writing. But human nature hasn’t changed much in 4,700 years. People still love, hate, drink, eat, etc. – and they still fear death. Gilgamesh is the awe-inspiring, despotic king of Uruk. The gods answer his beleaguered subjects’ prayers in the form of Enkidu, a rival who becomes Gilgamesh’s friend. They embark on several heroic exploits and end up pissing off the gods. As a result, they condemn Enkidu to death. Despondent and fearing for his own death, Gilgamesh goes in search of the secret of immortality. His travels take him to Utnapishtim, immortal survivor of the great flood. Our hero finds a plant that restores youth, but loses it. By the end of the story, he accepts his fate as a mortal. The story moves fast and is surprisingly engaging. It includes early versions of ideas that would resurface later in the Bible. (Most obviously, Noah and the flood.) There’s also some material that probably wouldn’t pass muster in our prudish time. The Dhammapada is one of the central Buddhist scriptures. I was familiar with several of these texts but hadn’t read the whole thing. Gioa notes that he recommended it because of its length, but there are also obvious connections with Gilgamesh. For example, several verses in the Dhammapada deal with attachment. For example, here’s verse 215: From affection comes grief; Gilgamesh suffers from such an attachment. Here’s the moment of Enkidu’s death: He touched his heart but it did not beat, nor did he lift his eyes again. When Gilgamesh touched his heart it did not beat. So Gilgamesh laid a veil, as one veils the bride, over his friend. He began to rage like a lion, like a lioness robbed of her whelps. This way and that he paced round the bed, he tore out his hair and strewed it around. He dragged off his splendid robes and flung them down as though they were abominations. He wishes to hold on: Then Gilgamesh issued a proclamation through the land, he summoned them all, the coppersmiths, the goldsmiths, the stone-workers, and commanded them, ‘Make a statue of my friend.’ The statue was fashioned with a great weight of lapis lazuli for the breast and of gold for the body. A table of hard-wood was set out, and on it a bowl of carnelian filled with honey, and a bowl of lapis lazuli filled with butter. These he exposed and offered to the Sun; and weeping he went away. You can probably relate if you’ve ever lost someone dear. Human nature. Audiovisual Gioia recommended Stravinsky’s Rite of Spring and Wagner’s Overtures. I’m very familiar with both so I didn’t spend much time with either this week. For a new take on one of these familiar classics, check out Fazil Say’s astonishing piano version of the Rite of Spring. Here’s a short portion: Gioia also recommended looking at ancient Mesopotamian art. I didn’t spend as much time on this as I would’ve liked. That said, this introductory lecture provided context while highlighting major works of art and architecture: I took a different approach to cinema this week. Rather than go by an AI recommendation, I went down the old-fashioned route. (I.e., Google.) Specifically, I thought this would be a good opportunity to check out Iranian cinema. I’ve heard good things about Iranian films, but had never seen one. Googling led me to this article on Vulture. After reading through the list, I picked Abbas Kiarostami’s TASTE OF CHERRY. Yet again, I’ve gravitated towards a film about a middle-aged man in despair. (Is the Universe trying to tell me something?) Kiarostami effectively uses a minimalist style to explore what makes life meaningful despite (or perhaps because) of its finitude. Reflections There’s a pattern here. This week’s works dealt with core issues people have grappled with since we became people. The big one: how do we deal with death? Not just the impending death of everyone we love, but our own. Gilgamesh offers the traditional “Western” answer: “I can’t even.” So, fight it! He looks for a MacGuffin that’ll let him go on living and perhaps brings his loved ones back. It’s an idea that has had many progeny in our mythologies. And it’s not just the stuff of fiction: the impulse is still alive and well. (Pardon the pun.) The Buddha offers a different approach: non-attachment. It’ll be easier to let go if you don’t become enmeshed with things, people, and your own sense of being. So you train your mind so it won’t hang on. (Even the idea of “your mind” is suspect.) The price: not feeling either extreme. No despair, no elation. Kiarostami’s film suggests a third approach: accepting the inevitability of death while reveling in the experience of being alive. (You could argue this is part of the Buddhist way as well.) I won’t say more in case you haven’t seen TASTE OF CHERRY, but suffice it to say the film employs a clever structural trick to wake you from your slumber. Grappling with these kinds of issues is the point of studying the humanities. Yes, I know you’re busy. I’m busy too. But some day, the busyness will stop – as will everything else. I’m committed to living an examined life, and that requires thinking about stuff we’d rather put aside so we can get on with the next Zoom meeting. Notes on Note-taking I’m also committed to the other point of this humanities project: learning how to learn better in this AI age. This week, I continued tweaking my note-taking approach. I took notes in the Drafts app as I read, building an outline as I go through the week. I wrote down the main points I learned and things I’d like to share with you. I then elaborated this outline on one of my morning walks. My mind works better when my body is moving and clear from the day’s detritus. I also tweaked my note taking approach around the readings. I had an LLM summarize the reading and then used that as a refresher to write a summary in my own words. I’ve done the same in previous weeks. What’s different now is that I then pasted my summary into a ChatGPT window with a simple prompt: I read The Epic of Gilgamesh. What is wrong with this description of the story?: Gilgamesh is king of Uruk. He’s described as the strongest and most beautiful man in the world. He’s also something of a despot. He befriends Enkidu, a wild man who is almost as strong as Gilgamesh. They go on several adventures, which entail opposing the wishes of one of the Mesopotamian deities. Eventually, the gods are angered and decree Enkidu must die. Grief-stricken, Gilgamesh goes in search for the secret of eternal life, only to learn that human lives are limited. He returns to lead his people with this newfound wisdom. The LLM offered a helpful response that clarified nuances I’d missed: Gilgamesh wasn’t “something of a despot”; he was a tyrant. The gods created Enkidu as a counterbalance to answer his subjects’ calls for relief. The taming and channeling of this force of nature through initiation into human pleasures is an important aspect of the story I’d left out. Details about Gilgamesh and Enkidu’s transgressions against the gods. (These seemed less relevant for a high-level summary.) The fact Gilgamesh isn’t just searching for immortality because he’s grief-stricken over Enkidu’s death; he’s also fearing for his own life. The end of my summary was wrong; the book doesn’t suggest Gilgamesh changed as a result of his experiences. This last point is important. In writing my summary, I made stuff up that wasn’t in the book. I attribute my error to the fact I expect closure from my stories. Gilgamesh precedes Aristotle’s Poetics; its authors were under no compulsion to offer the hero a redemption arc. Which is to say, humans hallucinate too – and LLMs can correct us. Up Next Next week, we’re reading ancient Egyptian literature. I couldn’t find an ebook of the text suggested by Gioia, so I’m going with another Penguin book, Writings from Ancient Egypt. I studied some Egyptian architecture in college, and look forward to revisiting this part of the world and its history. Check out Gioia’s post for the full syllabus. I’ve started a YouTube playlist to bookmark all the videos I’m sharing in this course. And as a reminder, I’m also sharing these posts via Substack if you’d like to subscribe and comment.
99% of the time I want my software to be as fast as humanly possible. I want UI elements that respond quickly, and I want keyboard shortcuts to do as much as possible. But 1% of the time, for whatever reason, I just like when a computer takes a long
Last month I completed my first year at EnterpriseDB. I'm on the team that built and maintains pglogical and who, over the years, contributed a good chunk of the logical replication functionality that exists in community Postgres. Most of my work, our work, is in C and Rust with tests in Perl and Python. Our focus these days is a descendant of pglogical called Postgres Distributed which supports replicating DDL, tunable consistency across the cluster, etc. This post is about how I got here. Black boxes I was a web developer from 2014-2021†. I wrote JavaScript and HTML and CSS and whatever server-side language: Python or Go or PHP. I was a hands-on engineering manager from 2017-2021. I was pretty clueless about databases and indeed database knowledge was not a serious part of any interview I did. Throughout that time (2014-2021) I wanted to move my career forward as quickly as possible so I spent much of my free time doing educational projects and writing about them on this blog (or previous incarnations of it). I learned how to write primitive HTTP servers, how to write little parsers and interpreters and compilers. It was a virtuous cycle because the internet (Hacker News anyway) liked reading these posts and I wanted to learn how the black boxes worked. But I shied away from data structures and algorithms (DSA) because they seemed complicated and useless to the work that I did. That is, until 2020 when an inbox page I built started loading more and more slowly as the inbox grew. My coworker pointed me at Use The Index, Luke and the DSA scales fell from my eyes. I wanted to understand this new black box so I built a little in-memory SQL database with support for indexes. I'm a college dropout so even while I was interested in compilers and interpreters earlier in my career I never dreamed I could get a job working on them. Only geniuses and PhDs did that work and I was neither. The idea of working on a database felt the same. However, I could work on little database side projects like I had done before on other topics, so I did. Or a series of explorations of Raft implementations, others' and my own. Startups From 2021-2023 I tried to start a company and when that didn't pan out I joined TigerBeetle as a cofounder to work on marketing and community. It was during this time I started the Software Internals Discord and /r/databasedevelopment which have since kind of exploded in popularity among professionals and academics in database and distributed systems. TigerBeetle was my first job at a database company, and while I contributed bits of code I was not a developer there. It was a way into the space. And indeed it was an incredible learning experience both on the cofounder side and on the database side. I wrote articles with King and Joran that helped teach and affirm for myself the basics of databases and consensus-based distributed systems. Holding out When I left TigerBeetle in 2023 I was still not sure if I could get a job as an actual database developer. My network had exploded since 2021 (when I started my own company that didn't pan out) so I had no trouble getting referrals at database companies. But my background kept leading hiring managers to suggest putting me on cloud teams doing orchestration in Go around a database rather than working on the database itself. I was unhappy with this type-casting so I held out while unemployed and continued to write posts and host virtual hackweeks messing with Postgres and MySQL. I started the first incarnation of the Software Internals Book Club during this time, reading Designing Data Intensive Applications with 5-10 other developers in Bryant Park. During this time I also started the NYC Systems Coffee Club. Postgres After about four months of searching I ended up with three good offers, all to do C and Rust development on Postgres (extensions) as an individual contributor. Working on extensions might sound like the definition of not-sexy, but Postgres APIs are so loosely abstracted it's really as if you're working on Postgres itself. You can mess with almost anything in Postgres so you have to be very aware of what you're doing. And when you can't mess with something in Postgres because an API doesn't yet exist, companies have the tendency to just fork Postgres so they can. (This tendency isn't specific to Postgres, almost every open-source database company seems to have a long-running internal fork or two of the database.) EnterpriseDB Two of the three offers were from early-stage startups and after more than 3 years being part of the earliest stages of startups I was happy for a break. But the third offer was from one of the biggest contributors to Postgres, a 20-year old company called EnterpriseDB. (You can probably come up with different rankings of companies using different metrics so I'm only saying EnterpriseDB is one of the biggest contributors.) It seemed like the best place to be to learn a lot and contribute something meaningful. My coworkers are a mix of Postgres veterans (people who contributed the WAL to Postgres, who contributed MVCC to Postgres, who contributed logical decoding and logical replication, who contributed parallel queries; the list goes on and on) but also my developer-coworkers are people who started at EnterpriseDB on technical support, or who were previously Postgres administrators. It's quite a mix. Relatively few geniuses or PhDs, despite what I used to think, but they certainly work hard and have hard-earned experience. Anyway, I've now been working at EnterpriseDB for over a year so I wanted to share this retrospective. I also wanted to cover what it's like coming from engineering management and founding companies to going back to being an individual contributor. (Spoiler: incredibly enjoyable.) But it has been hard enough to make myself write this much so I'm calling it a day. :) I wrote a post about the winding path I took from web developer to database developer over 10 years. pic.twitter.com/tf8bUDRzjV — Phil Eaton (@eatonphil) February 15, 2025 † From 2011-2014 I also did contract web development but this was part-time while I was in school.