flâneur — a map of the web's best reading

You Still Need to Think

calv.info · 584 words · saved by 1 readers

As coding agents become more capable and long-running, they don’t remove the human job of thinking. Someone still has to direct the work—set goals, choose constraints, and judge outputs. Everyone seems to recognize this in the abstract. But nobody seems to talk much about how the product shape fundamentally shifts the type of thinking required to write code. I'd argue that seemingly minor UX differences between different coding agents end up having a massive impact on how users spend their "thinking budget." With a remote-first product like Codex Cloud (not the CLI), the product encourages you not to spend time thinking while the agent is working and spend more time thinking about the end result that the agent gave. We intentionally didn't want users watching the agent invoking terminal commands, because the model works very differently than a human might. With an interactive product like Claude Code or Codex CLI, you naturally spend more time thinking about about specs and the high le

You Still Need to Think Calvin French-Owen / Writing Calvin French-Owen About Writing Bookshelf You Still Need to Think SEP 26, 2025 As coding agents become more capable and long-running, they don’t remove the human job of thinking. Someone still has to direct the work—set goals, choose constraints, and judge outputs. Everyone seems to recognize this in the abstract. But nobody seems to talk much about how the product shape fundamentally shifts the type of thinking required to write code. I'd argue that seemingly minor UX differences between different coding agents end up having a massive impa

Explore this link on the map →

related reading