Claude Code creator Boris Cherny: talk to AI like a coworker
Boris Cherny, creator of Claude Code, said in a post on X that there is "no secret to prompting" and that users no longer need long, heavily scaffolded instructions to drive modern models. In the Sonnet 3.5 era prompts mattered a lot, he said, but what matters now is telling the model three things: what you want it to do, how much effort to spend, and how it should verify it did the right thing. As an example, he shared a casual prompt asking Claude to build a piece based on a podcast episode, telling it to "spend more tokens" so the visuals would beat New Yorker or New York Times data visualization, and adding "maybe some watercolor." Responding to questions about whether that was too vague, Cherny said the latest Opus 5.5 model has excellent aesthetic taste and can judge for itself; he showed a beige-and-orange watercolor-style result.
It signals that prompting practice is shifting from step-by-step directions toward defining goals and success criteria.


Claude Code 創辦人 Boris Cherny 近日在社群平台 X 上分享他的提示詞心法,直言與 AI 溝通「其實沒有什麼祕訣」。他認為,隨著 AI 模型持續進化,使用者已經不需要再依賴冗長、過度結構化的死板指令來驅動模型完成任務;對多數工作而言,直接把 AI 當成同事來對話就已經足夠。
Cherny 指出,與其鉅細靡遺地規定 AI 每一步該怎麼做,不如清楚說明三件事:你要它做什麼、希望它投入多少努力與資源,以及它應該如何驗證自己是否做對。他強調,現代模型更需要的是明確的最終目標與成功標準,而不是繁複的流程腳本。
#Anthropic#Claude Code#Claude Opus 5.5#Boris Cherny#Claude#X