Run Data Run
SubstackBuilding in public. AI experiments, lessons learned, and the journey of treating AI as a multiplier.
I’m Justin Johnson. I Build Things.
justinhjohnson.com
The Robot on My Desk Learned to Dance
An experiment in agentic AI, building in public, and holiday side projects
I Built a Personal Memory System for Claude
(And You Should Too)
And Neither Could Do Alone...
100 GPU-Hours with an AI Research Partner
3 AM, A Phone, and a Time Machine
Building The Chronoscope Before Coffee
The Research Flywheel: Science That Compounds
Recursive Science, From Paper to Paper with Autonomous Research
Earlier posts (13 more)
The Genesis Simulation: A Memo from 2035
Looking back at the moment Science and AI merged—and the prompt that saved us.
The Death of the Blank Canvas
How Gemini and Claude Are Rewriting the Rules
Decoding AI in Cancer Research
A Practical Guide to Interpretability and What’s Next
The Future of Scientific Computing
Part 3 of 3: Nine Days of Petaflop Delegation
Compound Velocity: The 20-Hour AI Research Lab
Part 2 of 3: Nine Days of Petaflop Delegation - Building monitoring while fine-tuning while training while documenting while...
Delegation, Not Automation: How Human-AI Collaboration Actually Works
Part 1 of 3: Nine Days of Petaflop Delegation
From Petaflop to Production: Building a RAG Research Platform on the DGX in One Afternoon
Last week, I wrote about getting my NVIDIA DGX Spark up and running in three days.
Three Days, One Petaflop, and an AI Partner: Building a Research Lab
Building a GPU research lab with Claude Code, and documenting both what I built and how we built it
The Quiet Week Claude Became Your Coworker
Skills, Agents, and the Infrastructure Nobody Noticed
When the AI Picked a Drug Nobody Was Testing
How teaching an AI to read cells as text revealed a context-dependent cancer mechanism
From Workslop to Agentic Slop
How AI Agents Could Make a Bad Problem Worse
The $2B Bet on the 90/90 Rule - Thinking Machines and Tinker
Why Fine-Tuning Infrastructure Matters More Than You Think
Cancer AI Alliance: When Federated Learning Finally Works
Four cancer centers did in 12 months what the industry couldn't do in 10 years. Here's what actually changed.
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.