如何最大效能使用 AI 工具?

我在 Claude 团队工作。这是一段很有意思的经历：几乎每天，我都会发现有人借助 Claude 完成了某项壮举，而这些成就往往是我未曾考虑过、曾认为不可能做到，或者单纯因为缺乏好奇心和时间而未曾尝试的。

模型的能力并非均衡发展。正如数学家陶哲轩（Terence Tao）所言，模型“在某些方向令人惊叹，而在另一些方向却显稚嫩”。有些人成功驾驭了这些惊人的能力，仿佛翱翔于天际——看着大家用我参与打造的产品攀登难以置信的高度，十分令人着迷。但还有许多人仍在努力适应他们的新羽翼，困惑于除了询问“法国的首都是哪里”或“帮我把这封邮件润色得别那么生气”之外，模型到底还能做什么。

我和其他从事 AI 工作的人经常呼吁：在使用 AI 时，我们应当更有雄心（ambitious）。这已经成为了一句集结号角式的口号。每当我们看到令人赞叹的应用时，就会转发并写道：“我们的野心还不够大。”但我深知将这种建议付诸实践有多么棘手，因此，这里有一份关于“如何变得更有雄心”的操作指南。

我认为“雄心”可以分为四种维度：速度（Speed）、高度（Altitude）、深度（Depth）以及广度（Range）。

速度（Speed）： 用更少的时间完成同样的工作，这是 AI 经济价值的基本盘：如果你需要写代码，我用 Claude 能完成得更快。这一点已被广泛认知，且不需要在使用 AI 的方式上发挥太多创造力，因此本文略过不谈。

高度（Altitude）： 提升抽象层级，关注最终结果而非单一具体任务。

深度（Depth）： 像行业顶尖专家一样去审视和推演任务。不再停留于任务表层，而是深入一层，触及底层的原始数据、工具和根本问题。

广度（Range）： 借鉴多个领域的经验与方法，而非仅仅局限于任务表面所需的那一个领域，去调用那些你平时通常不会用到的知识、工具和技术。

我主要使用 Claude，但我的建议并不受限于特定模型。

高度（Altitude）

我们常随口将其称作“让模型在更高的抽象层级上运行”。当你给模型分配一项任务时，它执行的不过是你对“如何达成目标”所做的最优猜测。要在“高度”上更有雄心，不妨问问自己——接下来你希望发生什么？目标背后的终极目标是什么？ 去年年初，我还会让 Claude 帮我排查并修复单个软件崩溃；而到了后来，我直接要求 Claude 确保我们的应用程序“零崩溃”。

让我们以一个日常（甚至可以说是琐碎）的办公任务为例。假设你在一家名为 Acme Inc 的虚构公司，需要为季度业务回顾（QBR）制作一套汇报幻灯片（PPT）。如果你输入一堆数据，Claude 很乐意为你生成几张幻灯片；如果你提供模板，它也可以顺畅填入内容。但这很难与“发现新行星”相提并论。来看看一些具体的步骤，让我们的思路逐层提升雄心：

基础步骤： 大多数业务回顾都想知道本季度发生了什么变化、原因是什么、以及应该采取什么对策。克制住仅在模板里更新数字的冲动——尽可能把你能获取到的所有原始数据喂给模型，让它理解你的业务逻辑：“告诉我本季度发生了什么变化，背后的原因是什么，以及我们应该如何应对。”

进阶步骤： 会议（至少高效的会议）最终都应产出明确的决策。向 Claude 提问：“基于你目前了解到的所有情况，梳理出眼前最紧迫的三个决策是什么，并针对潜在的发展方向展开分析，分别列出正反两面的论据。”

高阶步骤： 季度业务回顾诞生于这样一个时代：那时需要人类耗费大量精力筛选数据、厘清数据背后的含义，并判断公司是否需要做出业务调整。你可以这样要求 Claude：“业务评审的存在是为了让管理层及早发现问题，把资金和人力调度到正确的位置。请设计一种比‘季度汇报 PPT’更好的机制来实现这一点，并结合我们以往的历史数据证明该机制能更早发现问题；同时让这套新方案与当前机制并行运行一个季度。”

“高度”策略在追求某种终极成果时效果最好，但在纯创意类任务中表现稍逊。判断何时适合在“高度”上发力的一个显著标志是：你是否需要为了手头正在做的事情去开会讨论。 当然，目前这一方法仍有局限（在 2026 年，“Claude，帮我去赚钱”对绝大多数公司来说单凭一句话还是行不通的），但我普遍发现：随着模型能力的增强，它们处理高层级抽象任务的表现也越来越出色。

“高度”也是构建持久工作流（将人类移出执行闭环、无需你反复输入一项又一项任务）的关键所在。要做好这一点，通常需要重构你的工作流程——为了让 Claude 能够自主确保应用程序零崩溃，我首先得保证它能轻松拉取崩溃报告，理解哪个应用版本对应哪次 Git 提交，并赋予它访问 Windows、macOS 和 Linux 环境的权限，使其能够真正独立地复现并验证修复方案。

深度（Depth）

有时候，你只是想把某一项具体任务执行得极其出色。在“深度”上拥有雄心，意味着促使模型去使用该领域最顶尖专家所采用的工具、技术、媒介和专业知识——并持续深挖，直到连那些专家都能从你的产出中获得启发。

继续沿用 Acme Inc 的季度业务回顾例子。假设 Acme 公司正面临用户流失（随着时间推移客户流失）的困境。我发现结合以下技巧非常有效：

坚持使用业内顶尖专家所使用的工具： 当被要求“表现得像个专业人士”时，模型往往只是换了套行业术语，而没有真正改变工作方法。要在深度上解决问题，我们必须使用顶尖数据科学家和统计学家同款的工具。当 Claude 倾向于生成简单的 Markdown 表格时，坚持要求它构建数据库和统计模型。你不需要预先知道专家用什么，Claude 通常心里有数。

设定看似离谱的目标，并告诉模型这完全合情合理： 你需要将网页加载时间从 10 秒缩短到 5 秒？不妨直接要求达到 200 毫秒。如果模型觉得某件事不可能办到，重申这完全是可解的，它只需要继续探索尝试。

挑战既有认知： 尤其在商业领域，许多我们坚信不疑的事情其实只是对现实的粗糙近似。将原始信息与数据提供给模型，让它以对抗性的视角去检验既有假设：“我们一直认为用户流失是由于上手引导（onboarding）体验不佳导致的。请尝试从原始数据中复现并验证这一推论。”

创造新知识： 这一点可以顺理成章地承接对既有认知的挑战——一旦 Claude 已经深入数据腹地，让它去探寻盲区：“基于系统日志构建一套能够复现去年业务情况的客户模拟系统。然后找出我们尚未察觉的最早流失信号，并证明该信号能在未参与训练的新数据上完成有效预测。”

引入外部裁判： 切勿让模型对自己打分评判。我相信随着模型智能的提升，这一问题终会解决，但在 2026 年 10 月的当下，我强烈建议引入外部验证机制。最理想的方式是提供一个可供模型直接运行并实时获取反馈的评估工具。

我经常使用的一个简短提示词（Prompt）：

“我希望这项任务更加深入，而不是范围更大。在重写任务前，请先列出：(1) 该领域的顶尖专家会做哪些我目前没有要求的事情；(2) 他们会从哪些最原始的材料入手，而不是使用已被加工整理过的数据；(3) 他们会使用哪些具体的方法和专业工具；(4) 除了你和我之外，还有什么客观指标或外部手段能证明结果是正确的。完成以上分析后，重写我的提示词，精确提出这些要求。”

广度（Range）

简而言之，在“广度”上拥有雄心，意味着我们从多个不同领域的视角来审视手头的工作——引入比过去在成本考量下所能承受的更多跨界学科。这并不是多么独到的洞见，每一部盗贼冒险电影（Heist movie）在前 30 分钟里都在忙着集结性格迥异、各怀绝技的团队成员。随着 AI 工具让多智能体系统（Multi-agent systems，包含多线程、编排器或单纯的子智能体）的运行变得越发轻而易举，要求 Claude 跨界引入额外领域往往能带来惊艳的效果。

将其付诸实践并不简单，需要你发挥创造力。直到我看到同事 Alex Albert 使用 Blender 渲染室内设计，我才想到可以用 Claude 为我的个人主页构建 3D 虚拟环境——尽管我以前做过电子游戏！然而，这也是我见证最多神奇瞬间发生的地方。

具体该如何操作？我通常采用以下方法：

尝试用动词替换名词： 这是来自汤姆·凯利（Tom Kelley）与乔纳森·利特曼（Jonathan Littman）著作《创新的艺术》（The Art of Innovation）中的一个经典技巧。季度业务回顾不是“一套 PPT”，而是“在 30 分钟内，让事务繁忙的人相信一个关于因果关系的故事，并在不确定性中做出决断”。提炼出动词之后，不仅能让我、也能让 Claude 更容易理解哪些领域能为这一目标带来独特且有价值的视角。

组建你的特遣队： 假设这套 PPT 必须达到极高水准，否则外星人就要毁灭地球——人类会组建一支怎样的梦之队？为了保证产出质量，我会拉入一位数据分析师、一位调查记者和一位编辑；如果需要现场演讲，或许还要加入动态视觉设计师和音频设计师；甚至还可以组建一支对抗性的“红方团队”，邀请一位做空机构研究员和一名法务会计师加入。这里很容易不小心滑向纯粹的角色扮演，这只会让上下文变得古怪而不会实质提升产出质量。使用这个方法的核心是寻找对应的学科领域与专业方法：不要让模型去“扮演”一个做空机构空头，而是让它像做空者调研仓位那样去执行具体的调研动作。

上述所有维度的雄心，都要求模型拥有可安装软件的计算机环境，以及对各类相关数据的访问权限（无论是通过 MCP 协议连接器还是其他途径）。目前已有大量工具让这成为可能，我非常建议大家配置使用。

历史早有先例

人类自古以来就常常受困于自己对“可能发生什么”的认知定势——更糟的是，我们通常只在极其狭窄的专业领域内信任自己的能力。众所周知，米开朗基罗当年极不情愿去画西斯廷礼拜堂天顶画——因为在他看来，自己是一名雕塑家，而不是画家。

在调研关于“雄心”的课题时，我发现心理学中对此有一个专门的概念：自我效能感（Self-efficacy）。简而言之，自我效能感高的人更坚信自身的能力，从而往往能在现实中取得更大的成就。研究表明，自我效能感是可以被激发的：洛克（Locke）和拉瑟姆（Latham）深入梳理了长达 35 年的目标设定研究，得出明确结论：被设定具体且高难度目标的人，其表现显著优于那些仅仅被告知‘尽力而为’的人。Stripe 联合创始人帕特里克·科利森（Patrick Collison）长期维护着一个“快速榜单”（Fast list），记录了人类在被赋予宏伟目标和严苛期限时所完成的种种奇迹。其中一些被充分印证的思维策略包括：

通过相信事情可行去攻克难关： 1939 年，乔治·丹齐格（George Dantzig）在加州大学伯克利分校的一堂统计课上迟到了。他把黑板上的两道题抄了下来，以为那是课后作业并按时交了上去——而实际上，那是当时统计学界尚未破解的两大著名世界难题。

目睹他人做成之后去突破极限： 数十年来，人类一直试图打破“4 分钟跑完 1 英里”的极限。罗杰·班尼斯特（Roger Bannister）于 1954 年 5 月首次打破该记录，但他作为这一纪录唯一保持者的时间仅仅维持了 46 天。如果你热爱跑步，会发现类似的突破正在马拉松破 2 小时的征程中上演：塞巴斯蒂安·索维（Sabastian Sawe）在今年 4 月的伦敦马拉松赛中跑出了首个官方破 2 成绩；而在同一场比赛中，亚军也同样突破了 2 小时大关。

通过允许自己失败去成就大事： 有一本书叫The Inner Game of Tennis，又译网球内心戏，我上周才发现这本书。该书的核心观点是：如果你拼命去用力，你反而打不出最好的比赛状态。我们工程师或许还记得 Linux 最初的发布宣言：“这只是一项业余爱好，不会搞得像 GNU 那样庞大而专业。”

自我效能感并非新问题，但在今天它变得前所未有地关键。置身于 AI 能力每隔数周就会发生飞跃的世界，我们需要一套全新的思维与方法，让我们敢于去做那些曾经未曾考虑过、甚至不敢相信可能办到的事。

--------------------

How to be more ambitious: A tutorial for humans with models

I work on Claude. It’s an interesting experience: Every day I learn about yet another feat accomplished with or by Claude that I hadn’t considered, didn’t think possible, or simply lacked the curiosity and time to try. This month, it may have helped discover a new planet, I’ve seen the first AI music video that I really like, and we are discussing a new era of math. 

Model capabilities don’t grow uniformly. Models are, as Terence Tao puts it, “astounding in some directions, while inadequate in others”. Some people manage to pilot the astounding capabilities and seem to be flying — it’s addicting to watch people reach incredible heights with the products I’ve built. Many others are still struggling to get their new wings to work, wondering what they’re good for beyond asking “What is the capital of France” or “Can you make this email sound less angry”.

I frequently proclaim (together with other people working on AI) that we ought to be more ambitious when using it. It’s become a rallying cry. Whenever we see something impressive, we repost and write “we’re not ambitious enough”. I understand how tricky it is to follow that advice, so here’s a tutorial on being more ambitious. 

I think of ambition in four types: Speed, Altitude, Depth, and Range. 

•Speed: The same work in less time, the bread and butter for AI’s economic value: If you need some code written, I’ll do it faster with Claude. Well established and requires little creativity in how you approach AI, so I’ll skip this one. 

•Altitude: Going up in abstraction and considering the outcome rather than the individual task. 

•Depth:Considering a task the way a field-leading expert would. Rather than operating at the task’s layer, we go one level deeper and touch the underlying data, tools, and problems.

•Range: Drawing on multiple fields rather than just the one the task might need at the surface, using knowledge, tools, and techniques you normally wouldn’t.

I primarily use Claude (duh) but my advice is not model-specific.

Altitude

We often flippantly call this “letting the model operate at a higher abstraction”. When you give the model a task, it’s executing your best guess at how to get the outcome you want. To be more ambitious in altitude, ask yourself — what do you want to happen next? What’s the goal beyond the goal? At the beginning of last year, I still asked Claude to fix individual crashes for me. Eventually I asked Claude to simply keep our apps crash-free. 

Let’s consider an everyday (dare I say mundane?) office task. You’re at Acme Inc, an imagined company, where you need to put together a deck for the quarterly business review (QBR). Given a bunch of data, Claude will happily make you some slides. Maybe you even have a template and it just needs to fill it in.That’s hardly comparable to finding a new planet, so let’s look at some concrete steps to make our approach more ambitious. We’ll start basic and get a little bit more ambitious with each step:

•As input, most reviews want to know what changed this quarter, why, and what should be done about it. Resist the urge to just update whatever numbers are in the template — give the model too as much data as you can get your hands on so it can understand your business: “Tell me what changed this quarter, why, and what we should do about it.” 

•Meetings (the good kind, anyway) ideally end with some decisions. Ask Claude: “Work out which three decisions are most urgent in the face of everything you’ve learned, and start working on potential directions with for/against arguments.”

•QBRs are from a time when good reviews required humans to carefully sift through data, figure out what the data means, and if the business should adjust. Ask Claude: “The review exists so leadership catches problems early and moves money and people to the right places. Design a better way to do that than a quarterly deck, show from our own history that it would have caught things sooner, and run it beside the current one for a quarter.”

The altitude approach works best if you really are after some ultimate outcome; it works less well for creative endeavors. A good tell-tale sign that ambition in altitude is a good idea is if you’re going to have meetings to discuss whatever you’re working on. There are currently limits (“Claude, go make money” doesn’t seem to work for most businesses by itself in 2026), but I generally see that models seem to be able to operate at higher levels of abstraction the more capable they become. 

Altitude is also where people find durable workflows that take the human out of the loop, making it less necessary for you to constantly update the model with task after task. Doing this well often involves changing your workflow — in order to let Claude make sure our app is crash-free, I first had to make sure it can easily fetch crash reports, understand which app version maps to what git commit, and give it access to Windows, macOS, and Linux computers so it can actually independently reproduce and verify fixes. 

Depth

Sometimes, you just want a task executed really well. Being ambitious in depth means pushing the model to use the tools, techniques, media, and knowledge employed by the best professionals in the field — and to keep pushing until even those people might learn something new from your work.

Let’s continue with our Acme Inc example of a quarterly business review deck. Assume for a second that Acme Inc struggles with some user churn (customer loss over time). I’ve found a mix of the following techniques useful:

•Insist on the same instruments used by the best in the industry: When prompted to act like a professional, models often switch vocabulary without actually switching methods. To work on our problem with depth, we need to use the same tools as the best data scientists and statisticians. When Claude reaches for markdown tables, insist on the use of databases and statistical models. You don’t necessarily have to know what the experts use, Claude usually does.

•Pick unreasonable goals and tell the model that they’re very reasonable: You need your website to load in 5s instead of 10s? Ask for 200ms. Does something seem impossible to the model? Reiterate that it’s very much solvable, it just needs to keep going. 

•Challenge what you know:Especially in business, a lot of things we believe to be true are rough approximations of reality. Give the model access to the raw information and data and ask it to adversarially check assumptions. “We believe churn is an onboarding problem. Try to reproduce that from the raw data.”

•Produce new knowledge: Easily tacked onto challenging what you know — once Claude is already deep inside the data, ask it to find blind spots. “Build a simulation of our customers that reproduces the last year from our logs. Then find the earliest signal of churn we don’t know about yet, and show it predicts on data it has not seen.”

•Use an outside judge: Do not ask the model to judge itself.I assume that this will eventually be solved with increasing model intelligence, but in October 2026, I implore you to insist on outside validation. Ideally that’s a tool the model can run to get feedback immediately. 

A simple prompt that often helps me:

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.

Range

In short, being ambitious in range means that we consider our work from the perspective of different fields — more fields than would have been economical in the past. This isn’t a particularly unique insight, every single heist movie spends the first 30 minutes assembling a diverse cast of characters and talents. As AI products make it easier and easier to run multi-agent systems (with multiple threads, orchestrators, or simply subagents), I’ve seen really interesting results by imploring Claude to bring in additional fields.

Putting this into practice isn’t easy; it requires you to be creative. Until I saw my colleague Alex Albert use Blender to render interior designs, I never considered using Claude for 3D environments for my homepage — even though I’ve previously made video games! However, this is easily where I see the most magic happen.

So, how do we do this? I use the following techniques:

•Try to replace the nouns with verbs: An old trick from The Art of Innovation by Tom Kelley and Jonathan Littman. A quarterly review isn’t“a deck”. It’s“getting busy people to believe a story about cause and effect, and to decide under uncertainty, in 30 minutes”. Having the verbs makes it easier for both me and Claude to understand which fields might bring in a unique and useful perspective.

•Assemble the crew: The deck needs to be amazing, otherwise aliens will blow up Earth. What kind of team will humanity get together? For production quality, I’d bring in an analyst, a journalist, and an editor. If it has to be presented, probably a motion and audio designer, too. It might be useful to employ an adversarial “red team”, too, so let’s bring in a short seller and a forensic accountant. It is easy to accidentally engage in role play, which will make your transcript weirder without improving the actual outcome. Use this method to find fields and techniques. Don’t ask the model to write a short seller, ask it to do what a short seller does to research their position.

All the ways in which I describe ambition require the model to have a computer with the ability to install software and access to all kinds of relevant data (either using MCP connectors or other means). Plenty of tools make this possible and I recommend that you use one.

We have been here before

That’s my concrete advice for how to be more ambitious. If you’re willing to stick around for a minute, I’d like to tell you why I think this is even necessary in the first place.

We humans have always been held back by what we believe possible — and what’s worse, we usually trust ourselves only in very narrow disciplines. Michelangelo famously didn’t want to paint the Sistine Chapel — you see, he was a sculptor, not a painter.

While researching the problem of ambition, I learned that psychology has a name for this: self-efficacy. In short, people with high self-efficacy believe in their own abilities more, and in turn actually accomplish more. There’s evidence that self-efficacy can be hacked: Locke and Latham pored over 35 years of goal-setting research to confidently proclaim that humans who are given specific hard goals perform better than those who are simply told to try their best. Stripe founder Patrick Collison maintains a “Fast” list, chronicling the many things humans have accomplished when given both audacious goals and tight deadlines. Some hacks that are well documented:

•Accomplish hard things by believing them to be possible: In 1939, George Dantzig showed up late to a statistics class at Berkeley, copied two problems off the blackboard, and handed in his solutions thinking they were homework. They were two unsolved problems in statistics.

•Accomplish hard things after watching somebody else do them: For decades, humans chased the four-minute mile. Roger Bannister broke it in May 1954 but remained the only human to do so for a mere 46 days. If you’re into running, we’re watching something similar happen to the two-hour marathon: Sabastian Sawe ran the first official sub-two-hour marathon in London this April. In the same race, the runner-up also broke the two-hour mark.

•Accomplish hard things by giving yourself permission to fail: Apparently everyone’s favorite business book is The Inner Game of Tennis, which I discovered just last week. The book’s core thesis is that you’re not playing your best game of tennis if you’re trying really, really hard. We engineers might remember Linux, announced as “just a hobby, won’t be big and professional like gnu”. 

Self-efficacy isn’t a new problem, but it is a more powerful one now. In a world where our abilities make leaps every couple of weeks, we need techniques that allow us to do things we didn’t really consider or believe possible.