Articles, thoughts, images, ideas, and updates.
Four unsolved problems blocking the agentic future: correctness, architecture drift, context scaling, and judgment.
A durable wrapper pattern for autonomous agents: Bash owns state, validation, recovery, and completion.
Pretext reinforces what serious AI-assisted engineering looks like: hard constraints, real oracles, tiny repros, rejection.
Two weeks of agent benchmarks taught me that variance is a cost problem, and the real fix was better tooling.
AI-native dev teams don't start with better models. They start with structure machines can actually read.
What the printing press taught me about AI, FOMO, and the decades-long game of technological diffusion.
Use Claude Code with your normal login or z.ai via shell wrappers, without swapping config or leaking tokens.
Software was already an awkward fit for copyright. AI turns that mismatch into a full-blown regime change.
Let an agent discover a messy web UI flow once, then export the exact tool commands as a deterministic bash script.
AI answer engines rewrite your prompts into queries. Understanding this translation layer explains the weird keywords in your GSC.
Analysis of AI agent architecture, dev tool reviews, and go-to-market strategies. Unsubscribe anytime.