Topic
Using Codex and ChatGPT as engineering collaborators — repository workflows, security reviews, automation, and the practical boundaries that keep the work controlled.
I tried the Visualizations preview with a dinner request, then changed the guest count, dietary split, and budget to see what really updated. The result was useful precisely because its assumptions were visible.
I connected Codex to IntelliJ's MCP server, then used a one-route Play 3 app to verify the connection with a real breakpoint and a live variable. The exercise also exposed Play's sbt layout and what Action[AnyContent] means.
I built a daily French-news webtoon with the Codex SDK, then moved its reader to ChatGPT Sites. Here is the actual architecture: local generation, a Worker API, D1 and R2 storage, and uploads that survive retries.
One button turns my open Scala file into a focused lesson. How I built a native IntelliJ panel with Codex, connected DeepSeek, and used an unfinished class as the first real example.
A real IntelliJ development instance, a Scala-focused plugin, and my own graphite theme and hoodie mascot. The architecture, desktop screenshots, and tests behind the first working milestone.
A generated character only becomes an identity when it survives the next prompt. I turned one navy-hoodie mascot, two successful references and a --manga switch into a small reusable Codex skill.
I applied for verified Daybreak access, completed the identity check, and mapped the next step: connecting my own GitHub repositories to Codex Security without giving up human review or scope control.