Cloud code boss says he hasn’t written any code by hand since November
Anthropic’s head of cloud code says he hasn’t written a single line of code by hand since November, as AI is taking over software development.
The head of one of the world’s most talked about AI coding tools says he has stopped writing code himself entirely and says the change has made his job more enjoyable, not less. Boris Cherny, creator and head of cloud code at Anthropic, said that since November, 100 percent of their production code has been written by AI. He has not edited even a single line by hand. Instead, he now spends his time reviewing code, checking for security and correctness, and deciding what should be built next.
❮❯
Speaking on Lenny’s Podcast, Cherney said he ships 10 to 30 pull requests every day, often with multiple AI agents running at the same time. “I have never enjoyed coding as much as I do today,” he said, noting that AI has removed repetitive and time-consuming parts of the work.
Coding without typing on Anthropic?
Cloud Code started as a small internal project at Anthropic and was not an instant hit when it was first released. Early users struggled to understand terminal-based AI coding tools. Over time, as the system improved, usage increased rapidly.
Cherney said cloud code writes now account for about 4 percent of all public code commits on GitHub. The stakes are higher when private repositories are included. Inside Anthropic, AI reviews each pull request before it is made by a human, acting as an automated check on code quality.
For Cherny himself, the transition to fully AI-written code happened slowly. Only a small portion of his work was written into early versions of Cloud Code. This figure increased throughout the year and crossed 100 percent in November. He hasn’t manually written or edited the code since then, he said.
Cloud code is no longer limited to just writing code when asked. Cherney said the system now looks at bug reports, user feedback and internal data, and suggests improvements or new features on its own. This has changed the way teams work.
In some cases, AI has solved problems faster than experienced engineers using traditional methods. Cherney described a situation where a new team member let Cloud Code find and fix the memory problem on its own, while he was still manually analyzing the problem.
This equipment is also being used for tasks beyond engineering. Cherney said AI now helps with project management, coordinating information in documents and handling routine work like email and internal coordination.
Cherney says jobs and titles may change
Cherney believes these changes will affect the way people think about tech jobs. As AI handles more of the actual coding, he expects the role of “software engineer” to change or disappear over time. Instead, people can focus more on deciding what to build and why to build.
He warned that this change would not be easy. “It’s going to be painful for a lot of people,” he said, especially as AI is penetrating areas like product planning that were once considered human-only roles.
For now, humans are still part of the process. Engineers continue to review AI-written code, especially where security and accuracy matter. But the direction is clear. AI is taking over the task of writing software, while people are increasingly providing guidance, supervision, and final decision-making.
Cherney said the pace of change has been difficult, even for those creating the technology. “It’s important to remember how unusual this is,” he said. “Things are changing faster than anyone expected.”
