-
Opus Scored 115 of 115. Every Mistake Left Was Mine.
I set out to test whether AI could stay within Dutch rental law. The models under test kept finding errors in my answer key. Six principles for building evals, each one paid for.
-
The Bitter Lesson Needs a Score
Let the algorithm search, the bitter lesson says. But every self-improving loop climbs something. Whoever defines that score owns the edge.
-
Has AI Already Killed Sales Training?
Tim Ferriss asked it about nonfiction. The answer for MEDDPICC is on your own calls. A free Claude plugin that audits every call against the framework and coaches every rep each morning, built in 48 hours.
-
The Swarm That Hunts for Asymmetric Upside
AI struggles to find the ideas that mint monopolies. I built an agentic system that farms the raw material and run it on real markets.
-
Outrunning the AI Hype Train: How I Built a Swarm to Read Research Papers Before YouTube Does
I found out about Hermes from a YouTuber with a few hundred thousand views. To my credit, I traced it back to a 30-year-old PhD thesis within an hour. But that is not the edge I want. The edge is reading the paper before anyone makes the video. So I built a swarm of agents that does the slog for me, runs all night, and turns a corpus into novel theses I can be first to test.
-
Past the Compliance Wall: How to Put an LLM to Work on European Medical Records Without It Ever Seeing a Name
When founders in regulated industries try to point an LLM at the data that actually matters, they hit the Compliance Wall. This post walks through Layer 1 of getting past it: a four-primitive architecture (recently named the Reasoner-Executor-Synthesizer pattern in the agent literature) running end-to-end on synthetic European medical records, hosted in Amsterdam, with an LLM driving and never seeing a single real name.
-
Your AI Second Brain Has a Quiet Search Problem
If you're already running an AI Second Brain on markdown plus grep, your search layer is quietly underperforming. After auditing 50+ memory repos, I picked the one that ships. Here's what changes when you swap grep for hybrid search.
-
I Hired 12 AI Agents to Read a Sci-Fi Novel. They Found My Business in Chapter 2.
I pointed 12 AI agents at Accelerando and extracted 230 business ideas in seven minutes. But the real goldmine wasn't the ideas - it was the mental models. I extracted Stross's post-scarcity reasoning patterns, tested them against my savings decisions, and compared them to traditional frameworks. The synthesis was better than either alone.
-
133 Forgotten Conversations. 9,529 Lines of Intelligence. Zero Monthly Fees.
I asked my AI second brain to extract knowledge from a year of meeting transcripts. It mined 133 conversations into 40+ contact profiles and 9,500 lines of structured intelligence. Then it built me a replacement for the transcription tool I was paying for. Overnight. While I slept.
-
I Used AI to Convince a Skeptic That AI Works.
A client candidly admitted he couldn't show AI-generated work to his customers. That confession gave me the key to unlock a different skeptic, one who'd been resisting for weeks. Here's how my AI second brain turned a casual insight into a research-backed argument in under ten minutes.
-
Simulated Darwinism for Brand Website Design Systems
How AI swarms turn design budgets into exploration, not deliverables.
-
Compound Swarmcrafting: Why AI Should Write Books Before You Let It Rebuild Itself
I let 86 AI agents write a book about swarm intelligence, then fed the book back to the swarm as its own upgrade plan, and it worked.
-
Swarm Intelligence: The Book 86 AI Agents Wrote While I Slept
I didn't write a single paragraph of this book. I described an outcome, went to sleep, and woke up to 431,000 words of working material distilled into a 54,000-word tactical field guide.
-
I Built an AI Workforce That Runs While I Walk, Talk and Sleep
Everyone's running Claude Code in Cursor. I was too. So I built an AI workforce manager where I describe the outcome, deploy swarms overnight, and only get pulled back in when they're stuck.
-
Why AI "taking our jobs" is the best thing that could happen to us
The execution bottleneck that has kept great ideas trapped in busywork is dissolving and what's left is pure creative potential.
Also on The Cognitive Shift
Get the next Let Them Run piece first.
One email a week. What we deployed, what broke, what it taught us.
One email a week on what we deployed, what broke, and what it taught us.
One email per week. Unsubscribe anytime.
Swarm Operators is a private circle of operators, builders, and leaders dissolving cognitive bottlenecks. Entry by application.
Three short questions follow, then a human reads your application.