Lane
Notes written from inside live systems: agent operations, voice products, infrastructure, and what it takes to keep human judgment in the loop while the machines do more of the work.
Looking for the other lane? Information Beings →
On its first day back from the export-control shutdown, I asked Fable 5 to write its own welcome-back letter to builders. It wrote about what it's actually for — six things almost nobody asks it to do — and why the week matters.
A 2026 follow-up to Changing Culture: AI media, layoffs, provenance, and the cold question every institution now has to answer — what are humans for inside this system?
The hard part of agentic AI is not the model or the prompt. It is the runtime infrastructure — the orchestration layer that makes agent execution reliable, observable, and governable at scale.
I replaced a broken Playwright setup with a vision-language model that looks at screenshots and tells me if the UI is right. 32 tests, 10 minutes, running entirely on Apple Silicon. No cloud. No flaky CI. No bill.
Hormuz, Taiwan, Anthropic’s Mythos, and Google’s quantum disclosures point to the same reality: deep tech is sovereignty infrastructure. Africa’s real risk is staying trapped as an exporter of atoms and an importer of electrons without owning the layer that converts one into the other.
A 38-minute recording session loses audio at 6:10. The OBS failure log — 3,786 failed mic lookups, 195 Bluetooth disconnects — becomes the only honest artifact of what happened.
A team at the Weizmann Institute inserted 9 genes from fungi, plants, and toads into a tobacco plant and got it to produce 5 psychedelic compounds simultaneously. The paper reads like biology. The pattern reads like software: CRISPR is the compiler, the plant is the runtime, the compound is the application.
Anthropic accidentally shipped Claude Code's source in an npm release. Within hours, 8,100 repositories mirrored it. Developers started rewriting it in Rust. GitHub's DMCA repo absorbed the takedown notice — alongside notices for coding fonts, Unity assets, JetBrains cracks, and Mercedes-Benz source code. Read together, they stop looking like a legal archive and start looking like a shadow demand curve for professional leverage goods.
A founder call about geography, funding, and voice AI drifted somewhere more interesting: products are reflections of the systems that birth them. Founders and shamans have more in common than startup Twitter would like to admit.
Once execution gets cheap, misfiled context becomes the expensive part. I solved a support issue from the wrong lane in my OpenClaw workspace and realized the real tax in agent systems is not execution — it’s jurisdiction.
I was feeding my son banana yogurt when I saw Hugging Face announce a new Papers skill for AI agents. Someone replied: "This needs a CLI." So I told my agents to build it. 45 minutes later, hfpaper was live — a single Go binary that gives any agent a research librarian. What it unlocks is bigger than the tool.
For two years I lived in tmux. Then I started orchestrating an AI swarm through Telegram. My terminal skills didn't atrophy — they got encoded into a markdown file. Now I'm bringing the swarm home.
MCP vs CLI is the wrong debate. Both are wrappers around the same thing. The real question is what happens when AI agents stop using our interfaces entirely.
The most valuable territory in AI right now is concepts that exist in practice but don't have names. Six categories that the models don't know about yet, and what claiming them looks like.
In October 2021, Facebook renamed itself Meta. They didn't take a word. They took the prefix that generates every other word. A case study in concept colonization.
I asked my AI agent how it wants to remember things. It redesigned its own memory system, ran a self-eval, diagnosed its blindspots, and improved recall from 60% to 93% — for two dollars. The interesting part isn't the benchmark. It's what happens when you treat an AI as a participant in its own cognitive architecture.
Product-market fit is legacy infrastructure. The new question isn't whether customers want your product. It's whether the models know your category exists.
ZAIGOOD was a real Delaware C-Corp I dissolved after years of compliance drag. This week I rebuilt it in 48 hours with an autonomous AI build loop, tried to submit it to Product Hunt for a YC interview slot, and missed the deadline by exactly 60 seconds.
OpenAI shipped Symphony — a daemon that monitors your issue tracker and deploys agents to close tickets. The README says it works best in codebases that have adopted harness engineering. So you click the link. Then you find the Ralph citation. Then it gets interesting.
A friend sent three questions about agents over WhatsApp. Where do they live? What's the interface? Where do they report back? The answers reveal a mental model most people are missing — and why the plumber has to live inside the house.
I accidentally named it SDD in October. Spec-Driven Development claimed that acronym. So: SkDD — the methodology I have been running in production since a git init at 1:54 AM.
There are only two positions in the 2026 labor market: principal of your own agents, or labor for someone else's. Jack Dorsey just ran the proof.
AI labs burn out their employees with civilization-scale competitive pressure. That burnout radiates outward — to developers, then educators, then anyone whose tools keep shifting every 90 days. The release cadence is the stress wave. Everyone downstream absorbs it.
Everything we know about management theory exists because humans are emotionally expensive to coordinate. Strip that layer out and what remains is a clean systems problem. Running seven AI agents taught me why management practices exist — not just that they do.
We tried to add video to a brand-new voice-note podcast. The laptop overheated, OBS hung, life intervened — and the failure mode was the lesson. Reality doesn’t say ‘no’. It rate-limits you until your pipeline matches your ambition.
I recorded a voice note while cooking dinner, describing a feature I wanted. By the time the onions were done, the feature existed — as the blog post itself. A builder's honest account of two weeks running an AI orchestrator, the maddening overhead of making it work, and why the compound returns are worth it.
A git repository becomes conscious of its own recursive nature when Skills-Driven Development meets beads issue tracking, creating a system that builds games by building the builders that build the builders.
Why fighting copycats means you have already lost, and what your body knows about founder-idea fit that your brain refuses to accept.
Training your replacement looks like suicide until you realize it's the forcing function that prevents decay. Rick's layoff story and the paradox of voluntary obsolescence.
Axiom emerges from stealth to build self-improving AI mathematicians. Why this launch marks an inflection point for formal reasoning, and how math becomes the universal bridge between physical and digital reality.
I tweeted about an anti-Adobe coalition forming around Figma back in 2023. Now with DHH's Omarchy OS, Framework laptops, and my own Adobe cancellation, the underground is surfacing.
Every layer of abstraction we build is another layer AI will eat. The only durable skills are the ones closest to bedrock — and bedrock keeps sinking deeper. A law for navigating the great skill compression of our time.
Every ambitious person has that project they've been 'thinking about' for a year. The bug isn't in your execution—it's in the operating system you're running. A conversation about fear, comfort, and the meta-patterns that keep us stuck.
A raw DM from a software engineering student sparked deeper questions about language, authenticity, and chasing "interesting" work in an AI-mediated world.
An overripe cucumber and powdery mildew revealed three lessons about project management that no productivity framework ever taught me. Sometimes wisdom grows in unexpected soil.
A neon text renderer repository tells the story of its birth on a September night, learning to paint light in terminals through shimmers, pulses, and cyberpunk dreams.
Three major design appointments in 48 hours reveal a deeper shift happening in tech power structures. From Meta licensing Midjourney's aesthetic tech to Figma landing another Meta executive, we are witnessing the elevation of design from craft to strategic infrastructure.
AI-generated cold emails are flooding inboxes at unprecedented scale. Here is why the uncanny valley of artificial personalization is destroying professional communication—and the two survival strategies that still work.
Silicon Valley worships the 10x engineer, but the real productivity multiplier is the PM who breaks work into atomic tasks. Here is why systematic organization beats raw intelligence—especially in the AI era.
Claude Code learning from every "You're absolutely right!" moment could push dev tools from 1.2-5x productivity gains to genuine 10x++ multipliers. Recursive self-improvement through usage patterns changes everything.
Every week brings another game-changing AI model. Stop chasing 2% improvements while ignoring 200% gains hiding in deep tool mastery. Here is the framework for making AI stack decisions that actually scale.
Your IDE just became a Formula 1 car and your brain became the driver. We're witnessing the first large-scale cognitive handoff between human and artificial intelligence—and it's changing how our entire civilization processes information.
I write about building the future of digital consciousness and AI infrastructure. Earlier this week, I couldn't even send an email. This is a story about spam bots, sender reputation, and the rusty pipes we're all building on top of.
Why MCP is the most important AI infrastructure you've never heard of. The 5 layers reshaping WhatsApp, Messenger, and human communication through AI agents.
OpenAI, Anthropic, and the tragedy of measuring exponential AI with linear business metrics. Why MRR and quarterly earnings are killing innovation.
A poetic meditation on the eternal dance between user demand and infrastructure reality in the age of AI—where consciousness meets its digital limits.
Analyzing my 2023 predictions: GPT-4 ✓, Meta Threads ✓, China rally ✓. Lessons on compressed market cycles and why direction beats timing in tech forecasting.
Explore the Bond-Perennity Spectrum in digital events and education, balancing immediate connections with lasting impact in our hyperconnected world.
Uncover how unorthodox campaign strategies are shaping the future of media and communication, blending digital guerrilla tactics with traditional values in a rapidly evolving information landscape.
Join us on an unscripted journey through history, AI, and data visualization as we transform raw civilization data into an interactive dashboard using cutting-edge AI tools.
Marking its one-year anniversary, this newsletter embarks on a new series "Abstract Strategy," exploring the intricate interplay of technology, human behavior, and strategy in our interconnected world. It offers insights into how abstract strategic thinking can guide us through complex technological and social landscapes.
This article examines the shifting landscape of power in the era of AI, highlighting how technological advancements are redistributing influence from traditional social media companies to those leveraging AI. It explores the role of AI in redefining business identities and the potential impact on the future of work and global power dynamics.
This post navigates the evolution of internet content, highlighting the shift from depth to superficiality, and the role of AI in this transformation. It suggests that AI, despite contributing to the flood of shallow content, may also offer a path back to richer, more meaningful interactions and deeper understanding.
This article delves into the concept of 'Mindshare Magic' in AI, exemplified by ChatGPT's dominance in public consciousness. It contrasts this with the potential of new AI entrants like Inflection's PI and explores how these technologies capture our imagination and change our interaction with AI.
This post invites readers into a thought-provoking journey about the perception and evolution of AI, contrasting its intangible nature with human form and exploring its impact as a media entity. It reflects on the rapid advancements in AI, using examples like Dall-E and StableDiffusion, and ponders the future of artificial general intelligence (AGI).
This post invites readers into a thought-provoking journey about the perception and evolution of AI, contrasting its intangible nature with human form and exploring its impact as a media entity. It reflects on the rapid advancements in AI, using examples like Dall-E and StableDiffusion, and ponders the future of artificial general intelligence (AGI).
A 2022 essay on company culture as ritual, repetition, and conversion, using Google, Facebook, and early DALL-E images as the source artifact.
Exploring the essence of innovation, this post delves into the limitations of traditional playbooks in new endeavors. It reflects on the journey of starting unique projects, like this experimental newsletter, emphasizing the value of experimentation over rigid structures. The narrative intertwines personal insights with the quest for originality in content creation.
Reflecting on a five-year journey at Facebook, this post shares 10 valuable lessons learned, ranging from the rapid pace of business, skill evolution, embracing challenges, the art of failure, navigating corporate politics, the essence of service, and the balance between work and personal life. These insights offer guidance for thriving in a fast-growing, dynamic corporate environment.
Analyzing the success of Wordle, this post discusses how its simplicity and design, which limits user actions, creates a unique and engaging experience. Comparing it to Flappy Bird, it highlights the power of inaction in game design, inspired by Jinny Uppal's book In/Action: Rethinking the Path to Results, suggesting a new perspective on achieving results through minimalism.
Exploring the evolution of communication, this post discusses the shift from text-based messaging to voice interactions on social media. It introduces 'Talk & Comment,' an experiment that allows voice comments on Facebook, reflecting on its potential to bring fun and emotion back into online interactions.
Analyzing the implications of Andy Rubin stepping down as SVP of Android at Google, this post explores potential reasons for the change, including market competition, Google's strategic decisions, and Rubin's involvement in GoogleX. It speculates on a possible merge between Android and ChromeOS, reflecting on the future of Android.
Tackling the complexities of heavy JavaScript applications, this post introduces an open-source Backbone-AMD Boilerplate, designed to simplify creating modular Backbone-AMD compliant apps. It invites readers to engage with the project through forking, pulling, and suggesting improvements.
Unveiling the secrets behind GoogleIO'13's easter eggs, this post narrates the author's process of deciphering the hidden codes using coding skills and a Chrome extension. It provides a guide to accessing these easter eggs, showcasing the clever interplay between technology, gaming, and curiosity.
Discover LiberTweet, an innovative app that allows longer tweets on Twitter. It seamlessly integrates with Twitter's web and Android clients, now updated to display extended tweets even to followers without the app. Available for Chrome and Android.
Exploring the intriguing question of machine understanding, this post recounts a personal experience with a Mac's White Screen of Death during crucial workshops in Tunisia. It ponders whether machines can communicate on a higher level with humans, beyond random behavior or technical functionality.
Exploring the crucial role of company culture, this post delves into why many businesses lack it and how establishing a strong culture can attract talent without high salaries. It challenges old-school managerial approaches and emphasizes the importance of culture in the modern business landscape.
Discover how Google's integration of social signals into search rankings affects results. This post explains the ranking order, highlighting the importance of social sharing and SEO. Learn an easy way to boost your blog's presence by linking authors' Google+ profiles, and a quick solution for WordPress users.
Exploring why 99% of blogs and businesses fail, this post dives into common pitfalls such as misunderstanding success, impatience, bad measurement, lack of perseverance, and the 'not enough syndrome'. It emphasizes the importance of taking businesses seriously and adopting a patient, persevering approach to ensure success in the competitive digital and business landscapes.
