https://thecognitiveshift.com/ Nature solved distributed intelligence millions of years ago. Now it's your turn. en Thu, 08 Oct 2026 10:49:48 GMT https://thecognitiveshift.com/publications/let-them-run/ai-wrote-the-test/ https://thecognitiveshift.com/publications/let-them-run/ai-wrote-the-test/ Thu, 08 Oct 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/the-bitter-lesson-needs-a-score/ https://thecognitiveshift.com/publications/let-them-run/the-bitter-lesson-needs-a-score/ Fri, 02 Oct 2026 00:00:00 GMT Let the algorithm search, the bitter lesson says. But every self-improving loop climbs something. Whoever defines that score owns the edge. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/has-ai-already-killed-sales-training/ https://thecognitiveshift.com/publications/let-them-run/has-ai-already-killed-sales-training/ Wed, 09 Sep 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/the-swarm-that-hunts-for-asymmetric-upside/ https://thecognitiveshift.com/publications/let-them-run/the-swarm-that-hunts-for-asymmetric-upside/ Wed, 02 Sep 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/deep-connection/six-ai-reviewer-agents-426-000-mistake/ https://thecognitiveshift.com/publications/deep-connection/six-ai-reviewer-agents-426-000-mistake/ Fri, 07 Aug 2026 00:00:00 GMT Two layers of AI checked the work. Neither one did the math. What caught the error was a gut feeling about the shape of a number, and gut feelings don't scale. The fix fits in one file. The Deep Connection Shaun Thresher https://thecognitiveshift.com/publications/let-them-run/outrunning-the-ai-hype-train/ https://thecognitiveshift.com/publications/let-them-run/outrunning-the-ai-hype-train/ Wed, 20 May 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/past-the-compliance-wall-llm-on-european-medical-records/ https://thecognitiveshift.com/publications/let-them-run/past-the-compliance-wall-llm-on-european-medical-records/ Tue, 12 May 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/your-ai-second-brain-has-a-quiet-search-problem/ https://thecognitiveshift.com/publications/let-them-run/your-ai-second-brain-has-a-quiet-search-problem/ Tue, 05 May 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/i-hired-12-ai-agents-to-read-a-sci-fi-novel-they-found-my-business-in-chapter-2/ https://thecognitiveshift.com/publications/let-them-run/i-hired-12-ai-agents-to-read-a-sci-fi-novel-they-found-my-business-in-chapter-2/ Thu, 23 Apr 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/from-conversations-to-custom-tools/ https://thecognitiveshift.com/publications/let-them-run/from-conversations-to-custom-tools/ Thu, 16 Apr 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/convincing-skeptics-with-their-own-words/ https://thecognitiveshift.com/publications/let-them-run/convincing-skeptics-with-their-own-words/ Wed, 15 Apr 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/simulated-darwinism-for-brand-website-design-systems/ https://thecognitiveshift.com/publications/let-them-run/simulated-darwinism-for-brand-website-design-systems/ Mon, 30 Mar 2026 00:00:00 GMT How AI swarms turn design budgets into exploration, not deliverables. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/deep-connection/60-is-where-claude-starts-lying-to-you/ https://thecognitiveshift.com/publications/deep-connection/60-is-where-claude-starts-lying-to-you/ Thu, 26 Mar 2026 00:00:00 GMT AI output quality silently degrades as your context window fills, and by the time you notice, the session is already cooked. The fix isn't a bigger context window — it's a single line in your status bar and a rule: stop at 60%. The Deep Connection Shaun Thresher https://thecognitiveshift.com/publications/deep-connection/how-to-build-a-self-learning-content-engine-part-1/ https://thecognitiveshift.com/publications/deep-connection/how-to-build-a-self-learning-content-engine-part-1/ Thu, 19 Mar 2026 00:00:00 GMT Most AI content workflows start from scratch every Monday. This one accumulates what works week-over-week, cutting editing time from hours to minutes and turning content decisions into evidence-based lookups. The Deep Connection Shaun Thresher https://thecognitiveshift.com/publications/let-them-run/compound-swarmcrafting-why-ai-should-write-books-before-you-let-it-rebuild-itself/ https://thecognitiveshift.com/publications/let-them-run/compound-swarmcrafting-why-ai-should-write-books-before-you-let-it-rebuild-itself/ Mon, 16 Mar 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/deep-connection/ralph-loop-in-reverse/ https://thecognitiveshift.com/publications/deep-connection/ralph-loop-in-reverse/ Thu, 12 Mar 2026 00:00:00 GMT The Ralph Loop doesn't care which direction you point it. When you flip it (or run Ralph in reverse), it doesn't build, it reads. And what it reads from an existing system is something most teams can spend months wishing they had discovered, a specification of what the code actually does, extracted from the code itself. The Deep Connection Shaun Thresher https://thecognitiveshift.com/publications/let-them-run/swarm-intelligence-the-book-86-ai-agents-wrote-while-i-slept/ https://thecognitiveshift.com/publications/let-them-run/swarm-intelligence-the-book-86-ai-agents-wrote-while-i-slept/ Mon, 09 Mar 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/i-built-an-ai-workforce/ https://thecognitiveshift.com/publications/let-them-run/i-built-an-ai-workforce/ Mon, 02 Mar 2026 00:00:00 GMT 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. Let Them Run Rhys Fisher https://thecognitiveshift.com/publications/let-them-run/why-ai-taking-our-jobs-is-the-best-thing/ https://thecognitiveshift.com/publications/let-them-run/why-ai-taking-our-jobs-is-the-best-thing/ Wed, 18 Feb 2026 00:00:00 GMT The execution bottleneck that has kept great ideas trapped in busywork is dissolving and what's left is pure creative potential. Let Them Run Rhys Fisher