Posts tagged “ai”
33 posts
I did not want another writing tool
The first question should be what do you know, not what do you want to write.
Every AI writing tool opens with a blank box and asks what you want to write about. Then the model invents something, and it reads like it was written by someone who has never done the work. The gap worth closing is not writing. It is the hour between knowing something and having published it.
How I use a BlackOps brain to track my deploys
A brain is a set of markdown notes the agent keeps and reads back. I backfilled 34 deploys into one and it found a failed build I had no record of.
I asked BlackOps for a brain called Deployment Log, backfilled 34 deploys into it out of the build logs, and it caught a failed build I had never recorded plus a fix I had already made too narrowly.
Claude's Watermark Has a Shelf Life
It marks assistance, not authorship. And assistance is about to be on everything.
Anthropic now watermarks Claude's text output worldwide. The mark works. It will also stop meaning anything, because assistance is on its way to being universal and a signal present on everything distinguishes nothing.
Slop Is What Falls Out When Nobody's Steering
Medium won't buy an AI detector. They're right, and the standard they're describing is one most human writing has never cleared.
Medium sent me an email about AI detection and answered its own question. Here is what actually separates writing worth reading from slop, and why twenty rules and an eval gate still didn't catch the bad sentence in this post.
The Work Starts When the Thought Does
An autonomous SDLC where a note fires a Claude session, and the pull request is waiting when I get home.
Self-healing software survives its bugs without changing a line. What I run against my projects changes the source. Logging the defect is what fires the work, and most days the completion email is the entirety of my involvement.
How I Use BlackOps to Reply on X Without the AI Slop
I run each Hunt as a live search on X, the extension scores the results and drafts only when something I actually wrote answers the tweet, and it tells me no the rest of the time. I send every one myself.
Everyone says reply to twenty tweets a day. BlackOps flags the three or four conversations where I actually have an answer, drafts from what I've written, and tells me no the rest of the time. Real replies, not AI slop.
A Year Into Wispr Flow, I Can't Work Without It Anymore
Bullet points in, full messages out. That's the whole unlock.
A year ago voice dictation felt like a gimmick. Now it's load bearing. Here's what actually changed once I stopped typing and started talking.
Your Obsidian Vault Is Full of Fossils.
Your brain rewrites memories every day. Your Obsidian vault never gets the chance.
If you use Obsidian, you have a daily note ritual. Open today's note. Pull up yesterday's. Copy the unfinished tasks forward. The daily note is supposed to be a living document. In practice, it's a stack of fossils you maintain by hand.
They Booed AI at Graduation. I Get It. They're Still Wrong.
A room full of arts and humanities graduates booed a speaker for mentioning AI. Their fear is legitimate. Their response is the exact thing that will accelerate the outcome they're afraid of.
Signup is dead. The agent is the signup form now.
From npx to a live post in ten minutes. No forms, no empty dashboard.
From npx to a live post in ten minutes. No forms, no empty dashboard.
Coinbase Founder Just Validated What I've Been Saying for Months
Brian Armstrong announced one-person teams running fleets of AI agents. I wrote about this model months ago. The only difference is he's calling it a pivot. I've been living it.
Why Your Best Work Gets 200 Views While Slop Gets 4.8 Million
The platform math that rewards repackaging over judgment, and why practitioners win long-term anyway
A thread doing 4.8 million views taught me what's actually wrong with technical content right now.
.webp)
I Killed the Browser Workflow for Content Creation. My Readers Still Live in Browsers.
BlackOps builds for browsers. You just don't need one to use it.
I've moved my entire writing workflow into a single Claude chat. Research, write, publish, distribute—all without leaving the conversation. My readers are still in browsers. I'm not.
From It's a Small World to the Haunted Mansion: A Blog Post Written in Claude Chat via BlackOps MCP
How a single conversation, no app switching, no copy-paste, went from breaking news to published post before the ride ended.
Obsidian just shipped official Claude Code skills. Here's what it means when your vault already runs a custom skill ecosystem. And yes, I sent this from It's a Small World.
The Algorithm Just Told Me You All Use the Same Tool
How repackaging tools, viral libraries, and AI content generators are building an audience of people who don't matter—and why practitioners can spot you immediately.
The Repackaging Economy (Revised)
Einstein Didn't Remember the Speed of Light
The Cognitive Offloading Revolution & Al Assistance.
Einstein famously said he didn't bother remembering things he could look up. Thirty years into this career, I think I finally understand what he meant.
I Was Trying to Buy a Truck. I Accidentally Discovered the Future of Note-Taking.
I spent an hour researching a truck purchase with AI. At the end I hadn't written a single thing down. Then I asked BlackOps to log it. That one moment changed how I think about what this product actually is.
Two Waves of Digital Transformation. Developers Win Both.
Every layer of automation creates a new layer of complexity that needs builders. That's been true for thirty years. It's still true now.
Every layer of automation creates a new layer of complexity that needs builders. That's been true for thirty years. It's still true now.
Open Claw Memory Is Brittle - Here Is How Chief and I Are Fixing It
Eight real failures from running an AI operations agent for a month. The problem isn't intelligence — it's architecture.
I Predicted One Senior Dev and an Army of Agents. Tonight It Happened.
Last year I predicted the future dev team: one senior engineer and an army of AI agents. Tonight, from a phone at Epcot, I watched 10 AI agents run a standup, find production bugs, debate priorities, deploy fixes, and verify them. The prediction is no longer a prediction.
Your AI Agent Already Had File Access. Here's Why Obsidian CLI Changes Everything Anyway.
Obsidian 1.12 shipped a CLI. The internet yawned. Agents could already read files. They're missing the point entirely.
My First Week with OpenClaw: From Skeptic to Believer
I spent 10 days building an AI workforce. Then Anthropic made my tool change its name. This is the real story — crashes, renames, and shipping anyway.
Why This Feature Shipped in Hours (And Why Most Don’t)
It wasn’t the stack. It was the architecture, planned with Claude Code.
A real feature shipped in hours — not because of AI magic, but because the architecture already fit. How planning with Claude Code made the difference.Untitled Post
What Junior Developers Should Be Focusing on in 2026
As AI collapses the middle of development, intent and judgment become the job
Discover what junior developers should focus on in 2026, from AI-assisted coding to core fundamentals, and learn how to adapt your skills to modern workflows.
Vibe Coding Isn’t the Problem - Vague Thinking Is
Why AI-assisted development exposes leadership, not recklessness
Discover why vibe coding is not the real problem in AI-assisted development and how clear thinking, intent, and constraints turn it into a powerful workflow
When AI Exposes a Leadership Problem
Banning the tool is easier than defining responsibility
Discover how AI can expose deeper leadership and communication problems, and learn what it really reveals about trust, culture, and decision making in teams
The Quiet AI Power Gap Most CTOs Are Creating Without Realizing It
When AI governance becomes selective convenience, your rule-followers fall behind and your culture starts to fracture.
CTOs face a growing AI power gap as quiet users gain leverage and honest engineers fall behind. Learn how culture, ethics, and leadership decisions shape AI risk
AI Could Make Your Team 10× Faster. Here’s Why Enterprise Won’t Let It.
AI isn’t the problem. Fear, politics, and outdated processes are.
AI can 10× developer productivity, but enterprise culture blocks it at every turn. Inside: the fear, politics, and outdated processes that keep teams from using the tools that would make them faster.
The Future Dev Team: One Senior Engineer and an Army of AI Agents
How Mission-Command Development is reshaping engineering productivity, architecture, and delivery in 2025
Learn how Mission-Command Development lets a senior engineer direct AI agents to deliver faster, higher-quality software in 2025’s competitive tech landscape.
How I Created Mission-Command Development (The Backstory)
How a single senior developer with AI agents can replace entire development teams, transforming software delivery from slow team coordination to rapid mission command execution.
I Asked AI to Make My Site 'Pop' — It Built Asteroids Instead
From a simple UI request to shipping a complete Asteroids game—discover how Claude Code transformed casual conversation into production-ready code with authentic 1979 arcade gameplay.
When AI Goes Off the Rails
A deep dive into managing AI agents in development teams, from initial magic to debugging hallucinations. Learn how prompt infrastructure and team guardrails are reshaping the modern developer workflow.