Agents, copilots, and where machine-written code holds up under review — and where it doesn't.
9 articles
Anthropic donated the Agent Skills standard to the Agentic AI Foundation on October 22. With a million skills published, here is how to treat them like any other dependency.
Flint is a free 40B mixture-of-experts coding model built for laptops. Here is the setup, the settings that matter, and the limits to check first.
Claude Sonnet 4.5 leaves the API on November 30, 2026. Sonnet 5.5 rejects prefill, thinking budgets and sampling settings, so here is the migration checklist.
Marcus Feld on prompting AI coding assistants: what actually matters for engineering teams making this call.
Marcus Feld on hallucinated dependencies AI coding: what actually matters for engineering teams making this call.
Marcus Feld on GitHub Copilot vs Cursor: what actually matters for engineering teams making this call.
Marcus Feld on autonomous coding agents: what actually matters for engineering teams making this call.
Marcus Feld on AI pair programming junior engineers: what actually matters for engineering teams making this call.
Marcus Feld on reviewing AI-generated code: what actually matters for engineering teams making this call.
