Claude Code creator urges users to describe goals, not dictate steps to AI
Boris Cherny, creator of Anthropic's Claude Code, highlighted the most common mistake users make when prompting AI models: over-instruction. Speaking at a Y Combinator event, Cherny advised users to shift from issuing step-by-step commands to describing the task, setting guardrails, and defining success criteria. He drew a parallel to leadership, suggesting the approach mirrors how effective managers delegate work. Cherny also challenged enterprises to rethink how they measure AI value, arguing that token-usage dashboards track activity rather than meaningful outcomes.
This is an AI-generated summary. ShortSingh links to the original source for the complete article.


Discussion (0)
Log in to join the discussion and vote.
Log in