Fetching from the wire…
01
02
03
04
05
06
07
08
Vibe Coding2026-07-11 · source-backed
Willison's framing has settled into a real split: vibe coding (intent-first, accept-without-reading, optimized for speed with Lovable/Bolt/v0) versus agentic engineering (correctness-first, Claude Code/Aider/Cline under structured oversight). The tell is process. Spec-driven SOPs, TDD-for-agents, and review gates are migrating from blog theory into default workflows. The leverage for a solo builder is picking the right mode per task instead of treating them as one activity.
Each link below shares sources, entities, or timing with this story.
Simon Willison has been writing software for over 25 years. He's one of the most disciplined, transparent engineers in the Python ecosystem. And yesterday he published an essay admitting he no longer reviews every line of code that Claude Code generates for his production proj...
Of 53 tracked agentic projects, 28 are coding agents, and the five fastest-growing tools, Claude Code, Gemini CLI, Codex, Cline, and Aider, are all in that category (Help Net Security). Security advisories cluster around n8n (57), Claude Code (22), AutoGPT (15), Dify (13), and...
Willison's guide is the closest thing to a consensus playbook for working with coding agents. Two chapters published: "Writing code is cheap now" (the economics shift) and "Red/green TDD" (the methodology). Combined with the Ladybird Rust port case study (25K lines of Rust in...
Simon Willison published a blog post today that crystallized something I've been feeling for months. The clean distinction between vibe coding (non-programmers using AI without review) and agentic engineering (professionals maintaining standards) doesn't hold up anymore. Not e...
Leaked screenshots from what appears to be an Anthropic beta show a feature called "Let's ship something great" that turns a natural language prompt into a complete, running application. Database. Auth. Live preview. One-click deploy. All inside the Claude interface. Dataconom...
ladybird.org — 25,000 lines of Rust written in approximately 2 weeks using Claude Code and OpenAI Codex. The methodology is the story: comprehensive test suite written first (by humans), human-directed architecture decisions, bounded scope per agent session (small focused prom...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.