AI建设

如何更具雄心:面向人类的模型指南

阅读量:50次 发布时间::2026/10/25

摘要说明

    我正在研究 Claude。这是一次非常有趣的体验:每天我都会了解到 Claude 所取得的种种新成就,那些是我之前从未想过的、认为不可能实现的,或者因为缺乏兴趣和时间而未曾尝试过的。这个月,它或许还帮助人们发现了新行星;我还看到了首部让我真正喜欢的由人工智能制作的音乐视频。同时,我们也在探讨数学领域的新时代。


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”.模型的能力并非同步提升。正如陶哲轩所说,这些模型“在某些方面表现极为出色,但在其他方面却不尽如人意”。有些人能够充分利用这些出色的功能,仿佛在飞翔一般;看着人们利用我所设计的工具取得惊人的成就,实在令人着迷。而还有很多人仍在努力让自己的“新翅膀”发挥作用,他们不知道除了回答“法国的首都是哪里?”或“能让这封邮件不那么带有攻击性吗?”之外,这些工具还能用来做什么。

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.我经常(与其他从事人工智能工作的人一起)呼吁:在运用人工智能时,我们应该有更宏大的目标。这已经成了一种口号。每当我们看到令人惊叹的成果时,就会重新分享这些内容,并写道“我们的目标还不够远大”。我知道要遵循这个建议其实很困难,因此这里有一份关于如何设定更高目标的指南。

I think of ambition in four types: Speed, Altitude, Depth, and Range.我认为野心有四种类型:速度、高度、深度和范围。

  • 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.速度:在更短的时间内完成相同的工作,这正是人工智能具有经济价值的根本所在。如果需要编写代码,使用 Claude 的话就能更快地完成任务。这种技术已经十分成熟,使用时也不需要太多创意,因此我就不再赘述了。
  • Altitude: Going up in abstraction and considering the outcome rather than the individual task.高度:从抽象层面出发,关注最终结果而非单个任务。
  • 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.深度:以领域内顶尖专家的思维方式来处理任务。我们不会只停留在任务的表层,而是进一步深入,去了解其背后的数据、工具以及相关问题。
  • 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.应用范围:不仅仅局限于任务表面上看似需要的那一个领域,而是会运用多个领域的知识、工具和技术,包括那些通常不会用到的方法。

I primarily use Claude (duh) but my advice is not model-specific.我主要使用 Claude(这还用说),但我的建议并不针对特定模型。

Altitude  海拔高度

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.我们常常随意地将这种做法称为“让模型在更抽象的层面上运行”。当你给模型分配任务时,它其实是在尝试以最佳方式来实现你期望的结果。如果想要追求更高的目标,那就问问自己:接下来你希望发生什么?最终的目标又是什么?去年初,我还让 Claude 帮我解决应用程序出现的故障问题;后来则要求它确保我们的应用程序不再出现故障。

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:让我们来看看一项日常的办公室任务吧(敢这么说的话,这其实是很平常的任务吧?)。你所在的公司叫 Acme Inc,你需要为季度业务回顾准备一份演示文稿。有了相关数据后,Claude 就能帮你制作出相应的幻灯片。也许你已经有模板了,只需填入数据即可。不过,这显然与发现新行星相比远远算不上什么了不起的成就。那么,让我们来看看一些具体的方法,让我们的目标更加宏伟一些吧。我们会从最基础的内容开始,每一步都设定更高的目标。

  • 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.”作为输入信息,大多数评估都希望了解本季度有哪些变化、变化的原因,以及应采取哪些措施。不要只是简单地更新模板中的数据——尽可能为模型提供更多数据,这样它才能真正理解您的业务状况:“请告诉我本季度发生了哪些变化、原因是什么,以及我们应该采取什么措施。”
  • 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.”会议(至少是好的那种会议)最好能得出一些决策。可以问问克劳德:“根据你目前所了解的情况,选出三项最紧迫的决策,然后针对这些决策分别列出支持与反对的理由,开始探讨可行的解决方案。”
  • 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.”QBRs 出现于这样一个时代:那时,要写出好的评估报告,就需要人们仔细分析数据、理解数据的含义,并判断企业是否需要做出调整。可以问问 Claude:“制定评估报告的目的是让管理层能够尽早发现问题,从而将资源分配到正确的位置。请设计一种比季度报告更好的方式来实现这一目标,用我们自身的历史数据来证明这种方式能更早地发现问题,然后试运行这个新方法一个季度。”

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.如果你真的追求某种终极目标,那么采用这种高目标导向的方式会更为有效;而对于创意类工作来说,这种方式的效果则较差。一个能表明高目标导向是个好主意的迹象是:你会召开会议来讨论自己正在处理的工作。目前确实存在一些限制(在 2026 年,“让 Claude 去赚钱”这种做法对大多数企业来说并不可行),但我认为,随着模型的能力不断提升,它们似乎能够处理更复杂、更抽象的问题。

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.在较高层次上,人们能够找到更为稳定的工作流程,从而减少对人工干预的需求,也就不必再不断通过各种任务来更新模型了。要实现这一点,往往需要调整现有的工作流程——为了让 Claude 能够确保应用程序不会出现故障,我首先必须确保它能够轻松获取故障报告,明白哪个应用程序版本对应哪个 Git 提交版本,同时还要让它能够在 Windows、macOS 和 Linux 系统上运行,这样才能独立地复现问题并验证修复方案的有效性。

Depth  深度

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.有时候,你只是希望某项任务能够被完美地完成。要真正做到卓越,就需要让模型运用该领域中最优秀专业人士所使用的工具、技术、方法以及知识;并且不断努力,甚至让那些专家也能从你的工作中学到新的东西。

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:让我们继续以 Acme Inc 的季度业务回顾演示文稿为例。假设 Acme Inc 面临着用户流失的问题(即客户逐渐减少)。我发现,结合使用以下几种方法会很有帮助:

  • 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.坚持使用业内最优秀的人所使用的工具:当被要求以专业的方式行事时,这些模型往往会更换用词,却并不会真正改变处理方法。要想深入解决我们的问题,就必须使用与最优秀的数据科学家和统计学家相同的工具。当 Claude 需要使用 Markdown 表格时,应坚持要求它使用数据库和统计模型。你不必知道专家们使用什么工具,因为 Claude 通常已经知道。
  • 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.设定不切实际的目标,然后告诉模型这些目标其实是非常合理的:希望网站在 5 秒内加载完成,而不是 10 秒?那就要求 200 毫秒即可。如果模型认为某个目标无法实现,那就再强调一次,这个问题完全是可以解决的,只要坚持努力就行。
  • 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.”挑战你的既有认知:尤其是在商业领域,我们认定的许多“事实”其实只是对现实的粗略估算。让模型能够获取原始信息与数据,让它以反向验证的方式来检验这些假设。“我们认为客户流失是个入职问题,那就试着从原始数据中找出相关证据吧。”
  • 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.”创造新知识:可以轻松用于挑战现有的认知——一旦 Claude 已经深入分析了数据,就可以让它帮忙找出其中的漏洞。比如“根据历史数据构建客户模拟模型,重现过去一年的情况;然后找出那些我们尚未察觉的客户流失迹象,并展示该模型如何基于未曾见过的数据进行预测。”
  • 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.请使用外部法官进行评判:不要让模型自己来评判。我认为,随着模型智能水平的提升,这个问题最终会得到解决,但在 2026 年 10 月时,我还是希望大家坚持采用外部验证方式。理想情况下,应该有一种工具,能让模型立即获得反馈。

A simple prompt that often helps me:一个经常能帮到我的简单提示:

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.我需要的是这个任务的更深层次版本,而非规模更大的版本。在重新编写提示语之前:(1) 说明该领域中最顶尖的专业人士会采取哪些我尚未要求的行动;(2) 指出他们会从哪种最原始的材料开始处理,而不是那些已经经过处理过的资料;(3) 说明他们会使用哪些具体的方法和工具;(4) 说明除了你和我之外,还有哪些方式可以用来验证结果的正确性。之后,请根据以上要求重新编写我的提示语。

Range  范围

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.简而言之,追求更广阔的视野意味着要从不同领域来考量我们的工作——涉及的领域数量比过去要多得多。这其实并非什么独到的见解,因为每部抢劫题材的电影都会在开头 30 分钟内引入各种不同性格和能力的角色。随着人工智能技术使得多智能体系统的构建变得越来越容易,我通过让 Claude 整合更多领域的资源,取得了相当有趣的结果。

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.要将这个想法付诸实践并不容易,这需要一定的创造力。在看到我的同事亚历克斯·阿尔伯特使用 Blender 来渲染室内设计之前,我从未考虑过用 Claude 来制作首页的 3D 场景——尽管我之前还开发过视频游戏!不过,我认为正是在这个领域里,才能展现出最神奇的效果。

So, how do we do this? I use the following techniques:那么,我们该怎么做呢?我使用以下方法:

  • 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.试着用动词来替换名词:这是汤姆·凯利和乔纳森·利特曼在《创新的艺术》一书中提出的一个技巧。季度回顾并非“一份报告”,而是“让忙碌的人相信某种因果关系,并在 30 分钟内于不确定的情况下做出决策”。使用动词后,我和克劳德就能更轻松地判断出哪些领域能够带来独特且有用的视角。
  • 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.组建团队:舞台效果必须出色,否则外星人就会摧毁地球。人类会组建怎样的团队呢?为了保证制作质量,我会请一名分析师、一名记者以及一名编辑加入。如果需要展示成果的话,或许还需要一名动效与音频设计师。另外,聘请一些“对手角色”也会很有帮助,因此可以请一名做空专家和一名法务会计师加入团队。

    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 like a short seller, ask it to do what a short seller does to research their position.很容易无意中陷入角色扮演的情境,这只会让输出内容显得更加奇怪,而无法真正改善结果。请使用这种方法来寻找合适的领域与技巧。不要要求模型以做空者的方式写作,而应要求它模仿做空者进行调研的方式。

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.我所描述的实现抱负的各种方式,都要求相关系统拥有能够安装软件的能力,并且能够获取各种相关数据(可通过 MCP 连接器或其他方式实现)。有许多工具可以实现这一目标,我建议大家使用这样的工具。

We have been here before我们以前来过这里。

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.这就是我关于如何更具雄心的具体建议。如果您愿意稍等片刻,我想告诉您,为何我认为这样做是必要的。

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.我们人类总是被自己认为“不可能做到”的事情所束缚——更糟糕的是,我们通常只在自己熟悉的领域里才信任自己。米开朗基罗就曾拒绝为西斯廷教堂作画,因为他是一名雕塑家,而非画家。

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:在研究“野心”这一现象时,我了解到心理学中有专门的术语来描述它:自我效能感。简而言之,拥有高自我效能感的人更相信自己的能力,因此也能取得更好的成绩。有证据表明,自我效能感是可以被提升的:洛克和拉瑟姆通过分析 35 年来关于目标设定的研究结果后得出结论——那些被赋予明确且具有挑战性的目标的人,其表现会优于那些只被要求尽力而为的人。Stripe 的创始人帕特里克·科利森还维护着一份“快速行动清单”,上面记录了人们在面对艰巨的目标以及严格的截止日期时所取得的种种成就。有一些已经被充分验证的有效方法:

  • 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.只要相信自己能够做到,就能完成艰难的任务:1939 年,乔治·丹齐格迟到了伯克利大学的统计学课程,他从黑板上抄下了两道题,然后把自己的解答当作作业交了上去。其实那两道题都是统计学领域中尚未被解决的问题。
  • 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.在看到别人完成某项艰巨任务后,自己再尝试去完成它:几十年来,人类一直在努力突破 4 分钟跑完一英里的纪录。1954 年 5 月,罗杰·班尼斯特成功做到了这一点,但此后仅有他一人能做到这一成就,而且这一纪录也只维持了 46 天而已。如果你喜欢跑步的话,那么现在类似的情况正在 2 小时跑完马拉松的比赛中发生:今年 4 月,萨巴斯蒂安·萨韦在伦敦首次完成了正式的 2 小时以内跑完马拉松的壮举。在同一场比赛中,亚军也打破了 2 小时的纪录。
  • 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”.允许自己失败,才能完成艰难的任务:显然,大家都最喜欢的商业书籍是《网球的内心游戏》,我是在上周才了解到这本书的。该书的核心观点是:如果过于拼命地努力,就无法打出最好的网球水平。我们这些工程师应该还记得 Linux 吧——当初它只是被视作一种爱好,不会像 GNU 那样发展成成熟的商业产品。

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. If you find more techniques that allow you to be more ambitious, please let me know!自我效能感并非新出现的问题,但如今它的作用愈发重要了。在一个人类能力每隔几周就能实现飞跃的世界上,我们需要一些方法,帮助我们完成那些原本认为不可能做到的事情。如果您能找到更多能让我们更具雄心的方法,请告诉我!


需要更多资料,请留言

您的联系方式会被永久保密,仅用于将资料传送给您。 *