Boris Cherny, the creator of Anthropic's Claude Code, said at a Y Combinator event on Saturday that a common mistake from Claude users is giving overly detailed, step-by-step instructions because they underestimate the tasks a model can handle. Cherny said users should be specific about the outcome while giving the model more freedom, recommending describing the task, setting the guardrails, and defining what a successful completion looks like. He added that his approach may not have worked six months ago, but it does with today's more capable models. Google Brain cofounder Andrew Ng shared a similar idea last year, calling it "lazy prompting," where users provide minimal instructions as models get smarter. Cherny estimated that there are probably dozens, if not hundreds, of useful abilities that have yet to be discovered.