Hi there 👋

I used Gas Town for a week. I ended up with three mayors, 141 orphaned Claude Code processes and a new appreciation for why agent orchestration is hard. Gas Town is Steve Yegge’s framework for orchestrating a fleet of coding agents. It shines when most of your work is pure code: lots of independent tasks, clear specs, and you mostly know what you want and don’t care how you get there. It falls apart when the work is heavily human-in-the-loop or ambiguous. Keeping Gas Town fed with beads that align with your project goals is the hard part. ...

AI, Jevons Paradox, and the Future of Software Engineering The year is 1994. A groundbreaking technology is proliferating—one that would expose all of human knowledge to everyone, anywhere in the world. Industries relying on information scarcity trembled. Newspapers, encyclopedias, travel agents, and countless others faced an existential threat. That technology was the Internet, and while it did eliminate many jobs, it created exponentially more. Entire categories of work—social media managers, SEO specialists, app developers—emerged that would have been impossible to predict. ...

Software systems exhibit a peculiar property: the more sophisticated they become, the more they tend toward catastrophic rather than graceful failure. This pattern isn’t unique to software - it’s characteristic of all complex systems, from neural networks to financial markets. But software’s rapid evolution and ubiquity makes it a particularly interesting case study. A complex system isn’t merely complicated. Rather, it possesses specific properties that make its behavior fundamentally unpredictable: ...

Nvidia is one of the largest companies in the world, frequently taking the top spot. It’s revenue is growing at an astonishing rate, with margins better than a lot of pure software businesses - something usually unheard of for hardware companies. All of this is on the back of a massive AI hype cycle. During a gold rush, you should sell picks and shovels. Nvidia is selling bulldozers. In this post, I will dive into the components of Nvidia’s competitive moat, its strengths and weaknesses, and the competitors trying to cross it. ...

Joshua Foer’s “Moonwalking with Einstein” is one of the rare books that I found worth rereading. In it, Foer, a young journalist, enters the bizarre world of memory competitions after being assigned to cover the world championship. He describes in vivid detail the unusual characters he encounters, mnemonic techniques he learns, and books he reads to help prepare him for the U.S. Memory Championship. The “memory athletes” he interviews are able to memorize a deck of cards in thirty-two seconds, recall over eighty thousand digits of pi, and recite the entire works of Shakespeare. Foer’s efforts pay off, and he becomes the U.S. Memory Champion by the end of the year. ...

Regardless of your views on David Goggins, it’s undeniable that he possesses an extraordinary level of persistence and willpower. Not only did he complete the grueling BUDS training for the Navy Seals three times, but he also finished US Army Ranger School and Air Force Tactical Air Controller training. He set a world record by completing 4,030 pull-ups in just 17 hours. Beyond that, he has finished over 60 ultra-marathons, triathlons, and ultra-triathlons. Remarkably, he achieved all this despite facing a challenging childhood, poverty, and battles with obesity, asthma, depression, and a heart condition. ...

We’ve lived with like ChatGPT for over a year now. Last year seemed to be the height of the hype cycle, at least for me. It felt like everyone, from friends to Uber drivers, was excitedly discussing the potential of this groundbreaking technology. However, as often happens with new technological advancements, the initial excitement has dimmed somewhat when faced with the reality of day-to-day use. The trough of disillusionment is real. In this article, I’ll mostly discuss the limitations of LLMs in technical tasks, though I believe these limitations apply to any sufficiently complex domain. ...

“The Coming Wave” explores the advantages and risks associated with a surge of emerging technologies. Authored by Mustafa Suleyman, a British artificial intelligence researcher and co-founder of DeepMind and Inflection AI, the book extends beyond just AI. It delves into the merits and drawbacks of other developing technologies, such as quantum computing and synthetic biology. In the initial sections of the book, the author paints a picture of the potential benefits of these emerging technologies, reading like utopian science fiction. It later shifts to outlining the potential threats, evoking a dystopian hellscape. The book ends with a series of recommendations on navigating the fine line between these two extremes. The following review reflects my interpretations of the author’s opinions, except where I specifically state my own views. ...

Sebastian Mallaby’s “The Power Law” traces the early history of the venture capital industry up to the present day, highlighting its significant impact on the development of technology. Contrary to common claims that venture capitalists (VCs) are merely opportunistic lemmings following trends, the book argues that venture capital requires genuine skill and provides various examples to support this claim. It covers successful venture capital investments in tech giants like Amazon, Apple, Facebook, and Google, as well as notable failures such as WeWork and Theranos. Mallaby argues that these failures cannot be solely attributed to “traditional” venture capital, as non-traditional investors outside Silicon Valley played a significant role. The book also explores the expansion of China’s venture capital industry through the involvement of Silicon Valley VCs and offers recommendations for policymakers on navigating VC investment in China amidst recent political tensions. ...

Jared Diamond’s Pulitzer Prize-winning book, “Guns, Germs, and Steel” begins with a question posed by a New Guinea politician named Yali: “Why do white men have so much cargo [i.e., steel tools and other products of civilization], and we New Guineans have so little?” The book attempts to answer this question by uncovering the historical and evolutionary reasons for the vast wealth disparities between nations. Diamond’s answer to the question is summarized as follows: “History followed different courses for different peoples because of differences among peoples’ environments, not because of biological differences among peoples themselves.” ...