🌀🗞 The FLUX Review, Ep. 200
July 31st, 2025
Episode 200 — July 31st, 2025 — Available at read.fluxcollective.org/p/200
Contributors to this issue: Justin Quimby, Erika Rice Scherpelz, Neel Mehta, Boris Smus, MK
Additional insights from: Ade Oshineye, Alex Komoroske, Ben Mathes, Chris Butler, Dart Lindsley, Dimitri Glazkov, Jasen Robillard, Jon Lebensold, Julka Almquist, Kamran Hakiman, Lisie Lillianfeld, Melanie Kahl, Robinson Eaton, Samuel Arbesman, Scott Schaffter, Spencer Pitman, Wesley Beary
We’re a ragtag band of systems thinkers who have been dedicating our early mornings to finding new lenses to help you make sense of the complex world we live in. This newsletter is a collection of patterns we’ve noticed in recent weeks.
“Yet a man who uses an imaginary map, thinking that it is a true one, is likely to be worse off than someone with no map at all; for he will fail to inquire whenever he can, to observe every detail on his way, and to search continuously with all his senses and all his intelligence for indications of where he should go.”
— E. F. Schumacher, Small Is Beautiful
📝 Editor’s note: It feels like just yesterday that we were publishing Episode 100. Thanks for your continued support, and we hope you enjoy this special edition for #200!
💗🧠 What’s truth got to do with it
People say Steve Jobs had a “reality distortion field.” He had an uncanny ability to insist something impossible was possible… and then make others believe it too. Technically, he was often wrong. But functionally, he was right. His stories weren’t accurate, but they were useful. They shifted perception just enough to change outcomes.
The tension between accuracy and usefulness is at the heart of how we navigate information, stories, and the social fabric they stitch together. We can look at this through a 2x2: one axis tracks how accurate something is, the other how useful it is to the person receiving it.
Practical clarity is accurate and useful. This is the space where information maps to reality and helps the listener: a precise medical diagnosis that guides treatment; a how-to guide that solves your problem. These truths are reliable and functional. But while they’re often treated as the gold standard, they aren’t always the most transformative. They anchor us, but they don’t always lift us.
Mythic resonance is inaccurate but useful. These are the stories that aren't factually true, but can change the world, in ways large or small. Jobs’s reality distortion field belongs here. So does a visionary roadmap or a compelling metaphor. Story, myth, and ritual also belong here. These narratives create motion. They energize teams, orient behavior, or stabilize belief systems. They may be wrong on paper, but they land in the heart.
Weaponized precision is accurate but not useful. This is the terrain of technically correct statements that distract or derail: bureaucratic exactitudes that confuse more than clarify; a technically correct statement that misdirects the questioner. “It depends upon what the meaning of the word ‘is’ is.” These statements fail not because they’re false (technically), but because they don’t help. When deployed with an intent to mislead, they can feel like betrayal.
Noise and misdirection are inaccurate and not useful. This is where outright falsehoods, misinformation, and empty signals live. These are the statements that are both factually and emotionally lies.
Yet it’s not as simple as this. Usefulness is always situated. A book that inspires one person might disgust another. A prototype that excites a designer might confuse a stakeholder. And what is useful to the speaker may not be useful to the receiver. Usefulness is relational. It's about the statement in the moment, in the context, to everyone involved in the communication.
Our emotional reactions tend to track usefulness more than accuracy. When people say they “felt lied to,” they’re often reacting not to the inaccuracy itself, but to the unhelpfulness. It didn’t land. It didn’t contribute. The speaker didn’t care. And in those moments, we might ask ourselves: what’s truth got to do with it, if it doesn’t help us live or act or relate more meaningfully?
Truth lives not just in what we say, but in whether it helps us make sense of the world together. In the end, truth isn’t just a matter of fact. It’s a matter of care. It’s not only what we know, but how we show up for the knowing of others.
📖🕰️ Looking back (and ahead) at “worth your time”
A special section for Episode 200.
Back in Episode 100, we had GPT-4 examine the books we’d recommended and suggest some new ones that our readers might like. For this special episode, we’re reprising the theme of AI-inspired lookbacks. This time, we had Claude 4.0 Sonnet analyze our recurring “worth your time” sections.
First, we had Claude zoom way out and describe the high-level topics and themes that our “worth your time” recommendations tend to explore. Here’s what it identified, verbatim:
The FLUX "Worth Your Time" section consistently explores:
Cybernetics & feedback loops - How systems self-regulate and evolve
Conway's Law in practice - How organizational structure shapes outcomes
Institutional epistemology - How knowledge flows through organizations and societies
Technology governance - How technical decisions embed political and social values
Complex systems emergence - Unintended consequences and phase transitions
Historical institutionalism - How past decisions constrain present possibilities
Science & technology studies - How technology and society co-evolve
Organizational learning - How institutions actually adapt (or fail to)
Economic complexity - Markets and finance as complex adaptive systems
Strategic thinking - Military history and decision-making under uncertainty
A good distillation of our favorite themes!
Next, we asked Claude to recommend some new writers and YouTubers who could help our readers explore each area in more depth. Below is a curated sample of its recommendations. We selected a diverse set of thinkers whom our readers may not have heard of before, and we added one representative link to each person’s work.
Complexity & Systems
Melting Asphalt (Kevin Simler) - Cognitive science and social behavior analysis. Outstanding pieces on signaling and social reality formation.
Science & Epistemology
Sarah Constantin - Biologist/entrepreneur who writes about scientific institutions, aging research, and how scientific progress actually happens.
Jose Luis Ricon (Nintil) - Writes detailed analyses of scientific progress, particularly in longevity research and institutional reform.
Organizational Behavior & Management
Charity Majors - CTO who writes about observability, but really about how technical and organizational systems co-evolve.
Commoncog (Cedric Chin) - Business strategy focused on tacit knowledge and organizational learning. Explores how companies actually build capabilities.
Design & Technology Criticism
L.M. Sacasas - The Convivial Society newsletter - technology criticism rooted in philosophy and history. His work on how technologies reshape human relationships is outstanding.
YouTube/Video Content
Asianometry - Jon Y's channel covering semiconductor industry history and Asian economic development with a systems perspective.
Steve Mould - Physics/engineering explanations that often reveal unexpected system behaviors and emergence.
Economics & Finance
Pseudoerasmus - Economic historian who writes incredibly detailed threads and posts about development economics, demographic transitions, and how economies actually develop. His work on the "Little Divergence" is phenomenal.
Technology & Society Analysis
Gwern Branwen - Probably familiar to some FLUX readers, but his statistical/experimental approach to everything from AI to genetics deserves more attention. His "Why So Few Matt Levines?" piece was actually cited by FLUX.
Dan Luu - Software engineer whose blog covers everything from computer performance to institutional dysfunction. His piece on why software is slow despite hardware improvements is a classic.
Military History & Strategy
The Scholar's Stage by Tanner Greer - Military history and strategic culture, particularly strong on how societies make decisions under pressure. His pieces on Chinese strategic culture and American institutional decay are outstanding.
Great stuff overall, and we’re excited to start reading some of these writers! Claude also mentioned several popular publications that you’re more likely to have heard about: Ben Thompson’s Stratechery, Venkatesh Rao’s Ribbonfarm, Byrne Hobart’s The Diff, and the YouTube channels Polymatter and 3Blue1Brown, to name a few.
🔬🛣️ What makes a good signpost?
A special section for Episode 200.
One question we get a lot is how we source news stories for our recurring “signposts” section. How do we find clues that point to unexpected trends and patterns amidst a tumultuous sea of noise, news, and content? And how can you train yourself to pick out such signals?
Truth be told, it’s more an art than a science (and one we haven’t mastered!), but for this episode, we thought it’d be interesting to have AI take a stab at it. We asked Claude 4.0 Sonnet to examine our signposts section and identify some attributes of “signpost-worthy” news. Here are some attributes it pointed out:
Systems-Level Implications: The stories chosen reveal broader systemic changes rather than isolated incidents. For example, Vietnamese e-commerce using spare fridges as distribution centers shows adaptation in logistics infrastructure, while AI bots enrolling in community colleges to steal financial aid reveals vulnerabilities in institutional verification systems.
Emergent Behaviors: Stories that show people or organizations adapting in unexpected ways, like Kenyan Uber drivers collectively ignoring Uber's rates and setting their own prices, or Ukraine building drone components domestically when Chinese supplies were restricted.
Edge Cases with Broad Implications: Seemingly quirky stories that illuminate larger trends, such as the .io domain potentially disappearing due to geopolitical changes, which reveals the intersection of digital infrastructure and international politics.
Technological Convergence Points: Stories where different technologies or systems intersect in novel ways, like researchers growing large lab-grown meat using circulatory systems, or Roblox using AI to generate 3D environments from text prompts.
Institutional Stress Points: News that reveals where existing systems are breaking down or being gamed, such as California using AI to write bar exam questions, or the detection that 18% of songs on a streaming platform are AI-generated.
These are good; the emergent behaviors bit is our favorite. We also like how Claude added some examples from the episodes it read. Note that we just told Claude to read our website, rather than stuffing all of our back catalog in the prompt, so it only looked at a sample of our episodes. Still, even that limited sample gave it the gist of our thought process!
Next, how would one (in Claude’s words) “develop a keener eye for trend-spotting” in the FLUX mold? Here’s the LLM’s take:
Look for Adaptation Under Pressure: Pay attention to how people and organizations respond to constraints or limitations. Ukraine's shift to domestic drone manufacturing when faced with supply restrictions is a perfect example of necessity driving innovation.
Follow the Money and Incentives: Notice when people find ways to exploit or work around systems, as these often reveal structural weaknesses or emerging opportunities.
Watch for Cross-Domain Spillovers: Look for when developments in one field affect seemingly unrelated areas - technological, social, political, or economic changes rarely exist in isolation.
Pay Attention to Scale Transitions: Notice when something moves from experimental to practical scale, like lab-grown meat achieving new sizes or TSMC's Arizona fabs matching Taiwan yields.
Spot Institutional Lag: Look for stories where technology or social behavior is evolving faster than the institutions meant to govern them.
Perhaps nothing mind-blowing, but it’s got the right ideas. We hadn’t actively thought about the scale transitions insight before.
Claude also mentioned that we seem to think a lot about “decentralization and adaptation,” “hidden dependencies or single points of failure in systems we take for granted,” and “a recurring tension between top-down attempts at control and bottom-up emergent behaviors.” Those are spot-on; we’d add exaptation, evolutionary pressures, trend reversals, regulatory arbitrage, “step function” discontinuities, and unintended consequences. Of course, we also love scientific discoveries, surprising impacts of emerging technologies, or straight-up bizarre news.
🔮📬 Postcard from the future
A ‘what if’ piece of speculative fiction about a possible future that could result from the systemic forces changing our world.
// In the AI land rush, how might Apple respond to the changing landscape?
// The last day of Apple’s WWDC in 2027.
Tim Cook walks onto the stage. “Thank you, everyone. We are really excited about all the things we’ve shared with you… But there is one more thing.”
<audience erupts in cheers of excitement>
“We are in an era of massive change. AI has changed the landscape of business and computing. Companies big and small all over the world are working to launch software and hardware faster and faster. And AI is blurring the boundaries between previously separate areas. What does it mean to search the internet? What does it mean to call someone?
“Apple is a company that has always done things a bit differently than others. And today, we are underlining that point. We are going to zig when everyone else zags. We aim to put yet another dent in the universe.
“We watch the Olympics every four years and are spellbound at the capabilities of focused people. We feel awe and joy watching the Olympics, and admire the dedication and time those athletes put in for training and preparation to transform themselves into something insanely great.
“As Steve said, ‘Focusing is about saying no.’ So starting in 2028, we are saying ‘no’. No to the annual grind of hardware releases. We will release 2028 versions of all our hardware systems. But we will not release a new iPhone, MacBook, iPad, or any other line for four years. The next iPhone will launch in 2032. The new iMac, 2032. New MacBook, 2032. Mac Pro, 2032.”
<gasps from the audience>
“Four years is time for Apple to make meaningful changes that will make you feel awe and joy using our products. As part of this change, we guarantee that all 2028 hardware will have full Apple software and services support for at least 8 years—no more need to chase the shiny new iPhone or the latest version of MacOS.
“Our stock will likely tumble. We’re betting over $200 billion in annual iPhone revenue on this shift. While other ecosystems will churn out hundreds of new phone models and dozens of MR headsets, we will build one. Let them sprint; we run the marathon. And when we cross that finish line in four years, it will be a new record.”
Tim continues to speak, but a frenzy erupts as journalists frantically type, investors check their phones, developers exchange worried glances, and watch parties at Apple’s competitors erupt into chaos…
© 2025 The FLUX Collective. All rights reserved. Questions? Contact flux-collective@googlegroups.com.