Claude code creator shares an evergreen leadership lesson for users
Boris Cherny, creator of Anthropic's Claude Code, advises users to stop over-specifying prompts with step-by-step instructions. He suggests that modern AI models perform better when given clear goals and guardrails rather than rigid, manual processes.
Why it matters
As AI capabilities evolve, users must shift from 'prompt engineering' to 'goal-oriented' interaction to maximize the efficiency and creativity of large language models.
The most common mistake Boris Cherny sees from Claude users isn't a bad prompt. It's too much prompt. Speaking at a Y Combinator event on Saturday, the creator of Anthropic's Claude Code said people routinely hand the model a numbered march order—do this, then this, then this—and then wonder why the result feels boxed in. His diagnosis is blunt: that style of instruction is a leftover habit, and today's models don't need it.What he recommends instead reads like something out of a management handbook, and that's roughly the point. Describe the task. Set the guardrails. Say clearly what a finished job looks like. Then get out of the way.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in