I'm skeptical. Pre-ChatGPT the models didn't understand tool calls or file editing so you couldn't really do targeted edits. So I really am not sure what they mean by this.

I mean, it's not impossible - I wrote a "coding agent" with GPT-3. It sucked balls. The idea was you write a Markdown spec file and the tool then compiled it to an equivalent source code one shotting it every time, but it hardly worked at all. The file changed too much every time and instruction following wasn't good enough, so it'd keep changing the interface exported by the file, and there were lots of bugs etc.

The GP misquoted the article. They actually wrote:

> Shopify has been using LLMs to build software since 2021

GitHub Copilot integrated into VS Code started becoming available that year. It’s definitely not a coding agent, but it was certainly LLM-assisted programming.