Run Data Run
SubstackBuilding in public. AI experiments, lessons learned, and the journey of treating AI as a multiplier.
Take the Cast Off
Anthropic deleted more than 80% of Claude Code's system prompt and lost nothing they could measure. I ran the same test on my own instructions. I now know the answer for one file out of ninety-three.
I moved my whole AI coding setup to a model that costs 40 cents. Nobody noticed the difference.
A two-year-old harness, ported in an afternoon, for under forty cents. Then the model that did it wrote this post.
Somebody Is Finally Checking
A contest opened eleven days ago has produced more reproduction attempts than the field's own dedicated effort has managed in any year. Whether that becomes a check on the literature turns on a...
Nobody Saves Money on the Model
A team just swapped in a model that costs twice as much per token, and their bill went down. Here is why that is not a paradox, and what it means for anyone trying to make AI cheaper at scale.
The Failure That Leaves No Corpse
Your management apparatus is built for known unknowns. AI collaborators mostly produce the other kind.
Workflows, Seven Weeks In
I called the economics of fan-out the day it shipped. Running it as a daily default since taught me the caveat I buried in a footnote is the actual problem.
Earlier posts (13 more)
It Spreads Sideways. Someone Still Has to Light It.
Anthropic's Claude Code lead published a five-rung adoption ladder this week. Microsoft published the measurement fifteen days earlier, and the two do not agree about the size of the prize.
The Loop Is Simpler Than It Sounds
A dumb little trick that keeps its progress on your hard drive, not the model's head, and the three questions that decide whether it pays off or burns you while you sleep.
Last 30 Days: The Loop
The 30-day sweep behind today's Run Data Run post: the moat thesis, the skeptics who got there first, the cost numbers nobody pitches, and the one stat I refused to print
Last 30 Days: The AI Scientists
Four autonomous discovery systems cleared peer review in four months. Every one of them was already a year old. Here is the full sweep, including the reliability research nobody is reading.
The Year Nature Caught Up
Robin found a new use for an old glaucoma drug and landed in Nature. The preprint was fourteen months old. Once you notice that lag, you notice it everywhere.
How I Actually Stay Current on AI (I Built a Wire)
The question I get asked most, and the system that answers it.
AI Ate the Keyboard. Now It Has to Eat the Queue.
Software stopped being the limiting factor. Process didn't. In biopharma and any patient-facing industry, the queue is the patient.
Every AI Book Tells You What to Think. This One Is About What Your Hands Do.
There is a whole shelf of AI books for leaders now. I read enough of them to know why I wrote a different kind.
The Gap, and the Book That Came Out of It
There's a line splitting the AI conversation that nobody's arguing about, because most people don't know it's there. I've spent months on the wrong-versus-right side of it. The book is out now.
Claude Science and the boring 80 percent
Anthropic shipped a workbench, not a miracle. The model is the commodity layer. The harness around it is the moat.
Borrowed Iron
A borrowed eight-GPU node, a global-health mission, and a crew of six: me, a founder, and four interns.
The Harness Is the Moat
The model is the part of your AI strategy you can order off a price sheet. The thing you build around it is the part nobody can copy. I made mine public so you can see the shape of it.
Ep. 1: Two Groups
Same AI, same task, a different result. The difference isn't the model.
Want more? Subscribe to get new posts in your inbox.
Subscribe on SubstackTechnical Deep Dives
In-depth technical articles from my AI research garden. Reference material on architectures, implementations, and emerging patterns.
Everything In The Family Holds The Key
Technical article
A Loop With Better Marketing
Technical article
Four Slots Left
Technical article
Tabular Foundation Models Got Acquired Before They Got Benchmarked
Technical article
Leading From The Other Side (The Month Three Checkpoint)
Technical article
From One Operator To A Team (The Phase Everyone Skips)
Technical article