AGENT RELIABILITY
|8 min read
Machine Learning 2.0
30 minutes to demo, 3 years to production. Why prompt tweaking won't survive. How ML 2.0 reframes AI workflow development.
Read articleEngineering the future of AI development
Blog
Insights on agent reliability, skills automation, token economics, and building systems that work.
LATEST
Deleting 40K lines of code failed on Opus 4.7, how did it do on 4.8?
|3 min read
We Have Stopped Developing Software.
Developers have stopped writing code and started training developer models. A mental model for the brute-Dev era: programming by examples, edge cases, and the Three Zones of Supervision.
|10 min read
The Signal Beneath the Noise
AI is not intelligence. It is a communication shift, a new paradigm to program machines simply by talking to them. Using this mental model will reframe how teams adapt, filter noise, and focus on what matters.
|12 min read
Are You Ready for the AI Coding Subsidy to End?
59.4% of tokens go to agents re-reading their own work. Demand for AI compute is outpacing supply, and prices are already climbing. The AI coding subsidy is ending. Here's what comes next.
|10 min read
We Read Claude Code's Leaked Source Code So You Don't Have To
512,000 lines of Claude Code accidentally went public. We checked every viral claim against the actual code - here's what was real, overstated, or invented.
|11 min read
How We Built This Website with Claude Code
A GTM lead, a senior dev reviewer, and Claude Code replaced a web agency. Here's the architecture behind Flowpad's website — and why the stack matters more than the tool.
|7 min read
From Neurons to Networks
AI agents aren't a factory assembly line. Complexity theory explains why they keep breaking, and why observability beats control.
|7 min read