A Medium post by WiredSis poses a fun thought experiment: hand Claude Code to a web developer from 2006 - someone who builds sites with jQuery, table layouts, and maybe early PHP frameworks - and see what happens.
The premise taps into a real tension in AI-assisted development. In 2006, "view source" was how you learned web development. CSS floats were still a mystery to most developers. AJAX was the hot new thing. Dropping someone from that era into a world where an AI agent can scaffold entire applications, run terminal commands, and refactor codebases in minutes would be genuinely disorienting.
The interesting question isn't whether a 2006 developer could use Claude Code - of course they could, since the interface is just a terminal. It's whether they'd trust it. Developers from that era had a deep-seated instinct to understand every line of code in their projects. The idea of an AI writing functions you'd ship without fully reading would have seemed reckless.
That instinct, honestly, is one a lot of current developers could stand to recover. The Slack API rate-limiting disaster covered elsewhere in today's news is a perfect example of what happens when AI-generated code gets shipped without that kind of scrutiny.
The full article is behind Medium's paywall, so we can't dig deeper into the author's specific arguments. But the premise alone is a useful thought exercise for anyone who's noticed their relationship with code changing since they started using AI assistants daily.