Substance Over Surface: Where Anthropic and OpenAI Agree on Reasoning
There is a comfortable intuition about making models safer. Show the model good behavior. Constrain what its reasoning is allowed to look like. Keep…
Essays & Field Notes
The Journal
Essays on agentic AI and distributed systems, and the architecture that keeps them working under pressure.
total
101
span
10 yrs
topics
7
The Agent That Finishes Is the One to Worry About
Most agent failures are easy to recognize. The tool call fails. The browser times out. The code does not compile. The agent loops. The…
Chat Is Universal. Agents Are Gated by Governance
Anthropic published a survey on May 27, 2026, of 1,260 social scientists, fielded in late February and March 2026. One pair of numbers carries…
The Harness Is the Control Plane: A Distributed Systems View of Agent Failures
Nine seconds. That is how long it took an AI agent to delete PocketOS's production database in late April 2026. The agent (Cursor running…
Why Your AI Agent Keeps Making the Same Mistakes
Your agent makes a mistake on Monday. You patch the prompt. It works on Tuesday. On Wednesday, a slightly different input triggers the same…
The Agent Runtime Era: Models Can Use Computers, Now Your Stack Needs To
For the last two years, the center of gravity in AI has been the model. Bigger context. Better reasoning. Better coding. Better benchmarks. That…
Repo Config Is the New Attack Surface for Coding Agents
A senior engineer opens an unfamiliar repo to review a PR. The coding agent wakes up and does what it was built to do.…
GitHub Just Put Agents in CI. Your Bottleneck Is Now Governance
Software delivery is becoming continuous inference. Agents don't just suggest code anymore. They act inside the delivery plane. And the first thing that breaks…
Reranking and the Recall You Throw Away
You added a reranker because retrieval quality was not good enough. The relevant passage kept landing at rank eight when it should have been…
Chunking Is Where RAG Silently Fails
You have tuned everything. A better embedding model, a reranker, hybrid search. Retrieval quality is still not what it should be, and you cannot…