
What happened
Asking Codex to build a Rails blog produced a PR with 139 changed files and about 3,800 added lines, which the author says he could not fully follow.
Why it matters
He now splits work into reviewable units and keeps logs of what was requested and changed, to avoid what he calls understanding debt.
Summaries like this, every morning.
The author came to Codex already comfortable writing Rails code himself and chose it because he was already a ChatGPT Plus subscriber. His first prompt was broad — build a blog, with a reference URL — and Codex generated the application, article list and detail pages, an admin screen, and tests, with Issue and PR text also written by the AI. The speed was real, but the gap between what the AI produced and what he understood became the central problem.
His response was procedural. He decided to check the AI's plan before implementation, split tasks into units he could review, and keep a log of what he asked for and what changed, a habit he traces to daily reports written during Fjord Boot Camp. He also read official documentation, listed unfamiliar terms such as context, skills, AGENTS.md, CLAUDE.md, agentic, and MCP, and read two books to organize the knowledge.
The Kamal incident shows why that discipline matters. A version-update thread led to a PR that passed RAILS_MASTER_KEY into Kamal's build settings, even though ReNovo runs on Render; leftover rails new configuration files had made Kamal look active. He removed the unnecessary Kamal settings while keeping what the Ruby update and Render build scripts needed, and concluded that a config file's presence says nothing about whether the technology is actually used. His stated goal now is to slow his judgment to a pace he can verify, rather than match the AI's output speed.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Goldman Sachs has barred employees who are not engineers from using advanced AI tools, as reported by Fast Com…

Visa launched its Agentic Commerce Benchmark, a framework to evaluate AI-powered shopping experiences for cons…

At the Next-Gen AI for Energy Summit in Houston on 3 November, Anthropic's Boaz Nur said AI will take over the…

Visa's Agentic Commerce Benchmark tested 22 AI models from 12 labs on shopping tasks like buying a TV or lapto…

Salesforce agreed to acquire Cresta, adding voice agents, real-time agent assistance, and conversation intelli…

In May 2026, SMFG said it will invest 100 billion yen in generative AI over three years, expanding a 50 billio…
