Subscribe
Sign in
Home
Podcast
RSVP for Boston Events
Free Field Guide
Lessons From the Trenches
Model Reliability Engineering
Vertical Agents
Archive
About
The "Self-Improving" AI Myth (And What 60 Production Deployments Actually Do)
Sixty production deployments converged on a three-layer architecture where the eval surface, not the base model, is the moat.
Jun 15
•
The AI Runtime
6
1
2
The Complete Field Guide to Browser Harnesses in 2026
Thirty-plus harnesses, four topologies, two billion-dollar valuations, one collapsing abstraction layer. The canonical landscape of how autonomous…
May 25
•
The AI Runtime
11
5
Model Reliability Engineering: Who Owns It When the AI Is Confidently Wrong?
Teams know their AI can be wrong. What's missing is the engineering discipline to make it reliably right.
Apr 8
•
The AI Runtime
27
3
5
Most Popular
View all
Model Reliability Engineering: Who Owns It When the AI Is Confidently Wrong?
Apr 8
•
The AI Runtime
27
3
5
How Vertical Agents Self-Improve in Production
May 2
•
The AI Runtime
16
2
7
The Anatomy of a Production Vertical Agent
May 19
•
The AI Runtime
20
2
3
The Complete Field Guide to Browser Harnesses in 2026
May 25
•
The AI Runtime
11
5
Claude Opus 4.7: The Production Engineer’s Breakdown
Apr 17
•
The AI Runtime
11
2
MCP Servers Are the Next Shadow Surface
May 15
•
The AI Runtime
10
2
Latest
Top
Discussions
Architecting the Auto-Updating Enterprise AI Data Loop
Tackling the AI Information Silos problem
Jun 22
•
The AI Runtime
6:07
AI Made Individuals Faster. Why Are Teams Still Slow?
The Next Bottleneck in AI Systems Is Context Transfer
Jun 20
•
The AI Runtime
1
1
16:40
State Machines for AI Agents: A field guide from Forward-Deployed Engineering
Agents reason. State machines remember.
Jun 18
•
The AI Runtime
1
8
Dario Amodei’s “Policy on the AI Exponential” Describes a World Banking AI Already Lives In
His new essay asks regulators to build an FAA for AI models. If you ship AI inside a bank, you already work in that regime, and there is a five-minute…
Jun 11
•
The AI Runtime
4
1
Harness Half-Life: A Field Playbook for Catching Agent Decay
The harness engineering discourse names what to build. The Model Reliability Engineering arc names how long the build lasts, what kills it, and what to…
Jun 8
•
The AI Runtime
3
The AI Eval Gate Cheat Sheet
Most AI projects die in the gap between "works in the demo" and "works in production."
Jun 8
•
The AI Runtime
1
Two Ways to Shrink an AI Model. Only One Keeps the Output.
Quantization changes the numbers. Lossless compression removes the wasted bits and keeps every output identical, for about 30% less memory.
Jun 7
•
The AI Runtime
1
18:36
See all
The AI Runtime
Free Field Guide to Production AI - https://substack.com/home/post/p-200392331 Production AI engineering, learned from those who ship
Subscribe
The AI Runtime
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
