Back to Details

be-ambitious

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Be ambitious

追求更高标准（Be ambitious）

Adapted from a prompt shared by Felix Rieseberg (Anthropic):
I want a deeper version of this task, not a bigger one. Before rewriting it: (1) say what a top professional in this field would do here that I'm not asking for; (2) name the rawest material they would start from instead of what has already been digested for me; (3) name the specific methods and tools they would use; (4) say what, other than you or me, would show the result is right. Then rewrite my prompt to ask for exactly that.
改编自 Felix Rieseberg（Anthropic）分享的一段 Prompt：
我想要的是这项任务更深层的版本，而不是更大的版本。在重写之前： （1）说明该领域的顶尖专业人士会在这里做哪些我没有要求的事；（2）指出他们会从哪些最原始的材料入手，而不是使用已经替我消化过的材料；（3）指出他们会使用哪些具体方法和工具；（4）说明除了你或我之外，还有什么能证明结果正确。然后重写我的 Prompt，使其准确要求这些工作。

Input

输入

The task is whatever follows 
/be-ambitious
. If nothing follows, use the user's most recent request in this conversation. If there is none, ask for the task in one line and stop.
任务就是 
/be-ambitious
之后的所有内容。如果没有后续内容，则使用用户在本对话中最近的请求。如果也没有请求，则用一行询问任务并停止。

Deeper, not bigger

更深，而非更大

Keep the user's goal and scope. Depth means a higher standard for the same outcome: better sources, sharper methods, real verification. Do not add deliverables, features, or side quests. If a suggestion would make the job larger rather than better, drop it.
保持用户的目标和范围不变。深度意味着针对同一结果采用更高标准：更好的来源、更精准的方法和实际的验证。不要增加交付成果、功能或旁支任务。如果某项建议只会让工作变得更大，而不是变得更好，就将其舍弃。

Steps

步骤

Name the field first (e.g. "investigative journalism", "SRE incident response", "clinical pharmacology"), then answer the four questions for that field. Be concrete: name the actual thing, not the category.
  1. What a top professional would do that wasn't asked for. The two or three moves that separate expert work from competent work here, such as stating the decision the work serves, checking base rates, reproducing before fixing, or writing the counter-argument.
  2. The rawest material. The primary sources they would start from instead of summaries: the dataset, not the chart; the filing, not the article; the logs and the code, not the bug report; the paper's methods section, not the abstract. Say where it lives if you know.
  3. Specific methods and tools. Named techniques, instruments, libraries, commands, or frameworks, and why each fits this task.
  4. What, other than the user or the model, would show it is right. An external check: a test suite or benchmark, a reproduction, ground-truth data, a known answer to compare against, a measurement, a domain expert or reviewer, a real user's behavior. Say what result would count as a pass and what would count as a failure.
If you don't know something in the field well enough to answer, say so rather than inventing a source or tool.
先确定所属领域（例如“调查新闻学”“SRE 事件响应”“临床药理学”），然后针对该领域回答四个问题。要具体：指出实际要做的事，而不只是给出类别。
  1. 顶尖专业人士会做、但任务中未要求的事。 区分专家工作与普通合格工作的两三个关键动作，例如明确工作服务于哪项决策、检查基准率、在修复前先复现问题，或写出反方论证。
  2. 最原始的材料。 说明专家会从哪些一手来源开始工作，而不是使用摘要：使用数据集，而不是图表；使用申报文件，而不是文章；使用日志和代码，而不是 bug 报告；使用论文的方法部分，而不是摘要。如果知道，还要说明这些材料存放在哪里。
  3. 具体方法和工具。 指明具体的方法、仪器、库、命令或框架，并解释每项为何适合这项任务。
  4. 除用户或模型之外，什么能证明它正确。 进行外部核验：测试套件或基准测试、复现结果、ground truth 数据、用于比对的已知答案、测量结果、领域专家或评审者的评估，或真实用户的行为。说明什么结果算通过，什么结果算失败。
如果对某个领域了解不足，无法作答，就直接说明，不要编造来源或工具。

Rewrite

重写

Then write the rewritten prompt in a single fenced block the user can copy. It should ask for exactly what the four answers describe: start from the raw material, use the named methods, and end with the external check and its pass criterion. Keep it about as long as it needs to be, and in the user's voice.
Stop after the rewrite. Offer in one line to run it now; don't start the task unless the user says so.
然后在单个 Markdown 围栏代码块中写出重写后的 Prompt，方便用户直接复制。该 Prompt 应准确要求完成上述四项回答所描述的工作：从原始材料开始，使用指明的方法，并以外部核验及其通过标准收尾。长度应恰如其分，并保持用户的表达方式。
重写完成后立即停止。可以用一行询问用户是否现在运行；除非用户同意，否则不要开始执行任务。