Coding for agents

Large language models (LLMs) and AI agents aren’t important to software engineering because they can write code at superhuman speeds. Without the right guardrails, as I’ve highlighted, that speed simply translates into mass-produced technical debt. No, agentic coding...

19 large language models for safety or danger

Everyone working on artificial intelligence these days fears the worst-case scenario. The precocious LLM will suddenly glide off the rails and start spouting dangerous thoughts. One minute it’s a genius that’s going to take all our jobs, and the next it’s an odd crank...

Why enterprises are still bad at multicloud

In 2026, most enterprises I talk to are multicloud, not because they set out with a crisp strategy but because reality pushed them there. Mergers and acquisitions bring in workloads on different platforms. Product teams pick the cloud that best matches a short-term...

Why local-first matters for JavaScript

The JavaScript innovation train is really picking up momentum lately, driven—as always—by the creativity of the JavaScript developer community. The emerging local-first SQL datastores crystalize ideas about client/server symmetry that have been a long time coming....