According to Anthropic's Claude Code creator Boris Cherny, the "common mistake" users make is giving lengthy prompts to micromanage AI, instead of trusting it to figure out the best way to complete a task. Speaking at a recent Y Combinator event, Cherny said many Claude users overload the AI with highly detailed instructions, leaving little room for the model to use its reasoning capabilities. He explained that users often dictate every step of the process instead of simply describing the desired outcome. Cherny stated that approach may have made sense several months ago, but the latest generation of AI models has become far more capable of independently determining how to solve complex problems. He encouraged users to assign AI "harder tasks" than they believe it can handle, revealing that Claude recently spent 11 days rewriting an entire production codebase from one programming language to another, a project that would have taken human engineers more than a year to complete. Cherny argued the future is about giving AI models more autonomy, stating "the verification I think is probably the single most important thing that people do not get right." He suggested people should treat AI "like you would a coworker."