Posts about coding-agents
-
Assume the LLM never ran
A 208 MB log, 59,356 retries, and zero LLM calls. A debugging story about what happens when the symptom lies about the cause.
-
Test-first dispatch for AI coding agents
The architect writes the tests. The implementer makes them pass. No prose specs, no circular validation.
-
Correctness is model-determined
I benchmarked four AI coding harnesses on 12 tasks using the same model. The harness barely matters for correctness — it's all about the model.
-
I made my coding agent dispatch system improve itself
mtor dispatched a coding task to improve itself — the tool that sends work to AI agents was improved by an AI agent.
-
What 16,000 Simon Willison posts reveal about the state of AI coding agents
Analysis of Simon Willison's blog corpus reveals AI coding agents crossed a reliability threshold in late 2025 and are now reshaping software engineering.