Between ChatGPT’s release in late 2022 and the end of 2024, I don’t yet have a method. I fumble, I explore, I pick up habits that will eventually cause problems. An idea settles in gradually: what makes a coding AI valuable isn’t the model, it’s the context you give it.
Late 2022: the first shock (GPT-3.5)
On November 30, 2022, ChatGPT launches. I try it right away and stay on it for hours. First intensive session with GPT-3.5: generating music, text, bits of code, testing ideas in every direction. At that point, it’s mostly curiosity: is this tech actually useful for coding? Short answer: yes, but not without guardrails.
The first scripts are sometimes impressive, but the tool also invents APIs, nonexistent imports, and anti-patterns. The lesson comes fast: AI can produce, but you have to verify. Human oversight stays central.
2023: GPT-4, Cursor, and context moving into the editor
On March 14, 2023, GPT-4 comes out, and I feel a real jump. From the first tests, the model understands better, reasons further, and writes more coherent code. It’s the first time I tell myself: “AI is starting to code almost like a colleague.”
Shortly after, I discover Cursor. The AI doesn’t feel like a plugin glued onto an editor: it sits at the center of the experience. I adopt it. What hooks me is the autocompletion: it’s no longer just syntactic, it starts adapting to the project.
Autocompletion has existed for years in code editors: type the beginning of a word, the tool suggests the rest. Before AI, it was mostly basic keyword completion from your own code. With AI, it changes scale: it anticipates what you’re writing, proposes entire functions, and adapts to project context. It’s continuous help, useful but demanding: quality depends on the context you provide (variable and function names, comments, pseudo-code), not only on the model.
That’s where the subject shifts: what matters isn’t only the model anymore, it’s what the editor lets it see of the project.
2024: Maturation
In 2024, out of caution, I don’t use AI directly on the codebases of professional projects. I still use it on the side: snippets, brainstorming, and especially reformulation.
I also observe daily life in large companies. I keep seeing the ceremonies and rituals that became standard for team synchronization. I step back from that machinery: it’s necessary, but the “coordination cost” of keeping everyone aligned is very real.