第一性原理-入门

这是一篇尝试给第一性原理祛魅的文章。

摘选部分 gpt4 和两篇第一性原理文章内容。

TFP: The First Principle.

A first principle is a foundational proposition or assumption that stands alone. We cannot deduce first principles from any other proposition or assumption.

一个合格(用 TFP)的教练行为:

Every play we see in the NFL was at some point created by someone who thought, “What would happen if the players did this?” and went out and tested the idea. Since then, thousands, if not millions, of plays have been created. That’s part of what coaches do. They assess what’s physically possible, along with the weaknesses of the other teams and the capabilities of their own players, and create plays that are designed to give their teams an advantage.

The coach reasons from first principles. The rules of football are the first principles: they govern what you can and can’t do. Everything is possible as long as it’s not against the rules.

马斯克对直觉的看法、以及典中典之马斯克论及火箭成本使用第一性原理的例子:

His approach to understanding reality is to start with what is true — not with his intuition. The problem is that we don’t know as much as we think we do, so our intuition isn’t very good. We trick ourselves into thinking we know what’s possible and what’s not. The way Musk thinks is much different.

Musk starts out with something he wants to achieve, like building a rocket. Then he starts with the first principles of the problem. Running through how Musk would think, Larry Page said in an interview, “What are the physics of it? How much time will it take? How much will it cost? How much cheaper can I make it? There’s this level of engineering and physics that you need to make judgments about what’s possible and interesting. Elon is unusual in that he knows that, and he also knows business and organization and leadership and governmental issues.”

Musk 说“反直觉思维”和“第一性原理思维”是他想建造可回收火箭这一想法的起点。

BuzzFeed 创始人对数字媒体的 FTP 运用:

After studying the psychology of virality, Jonah Peretti founded BuzzFeed in 2006. The site quickly grew to be one of the most popular on the internet, with hundreds of employees and substantial revenue.

Peretti figured out early on the first principle of a successful website: wide distribution. Rather than publishing articles people should read, BuzzFeed focuses on publishing those that people want to read. This means aiming to garner maximum social shares to put distribution in the hands of readers.

Peretti recognized the first principles of online popularity and used them to take a new approach to journalism. He also ignored SEO, saying, “Instead of making content robots like, it was more satisfying to make content humans want to share.”[8] Unfortunately for us, we share a lot of cat videos.

A common aphorism in the field of viral marketing is, “content might be king, but distribution is queen, and she wears the pants” (or “and she has the dragons”; pick your metaphor). BuzzFeed’s distribution-based approach is based on obsessive measurement, using A/B testing and analytics.

Jon Steinberg, president of BuzzFeed, explains the first principles of virality:

Keep it short. Ensure [that] the story has a human aspect. Give people the chance to engage. And let them react. People mustn’t feel awkward sharing it. It must feel authentic. Images and lists work. The headline must be persuasive and direct.

不知道是什么的 CD 公司的 FTP 运用:

When Sivers founded his company CD Baby, he reduced the concept down to first principles. Sivers asked, What does a successful business need? His answer was happy customers.當西弗斯創立他的公司 CD Baby 時,他將概念簡化為首要原則。西弗斯問道,一個成功的企業需要什麼?他的回答是讓顧客滿意。

Instead of focusing on garnering investors or having large offices, fancy systems, or huge numbers of staff, Sivers focused on making each of his customers happy. An example of this is his famous order confirmation email, part of which reads:

Your CD has been gently taken from our CD Baby shelves with sterilized contamination-free gloves and placed onto a satin pillow. A team of 50 employees inspected your CD and polished it to make sure it was in the best possible condition before mailing. Our packing specialist from Japan lit a candle and a hush fell over the crowd as he put your CD into the finest gold-lined box money can buy.

By ignoring unnecessary details that cause many businesses to expend large amounts of money and time, Sivers was able to rapidly grow the company to $4 million in monthly revenue.

In Anything You Want, Sivers wrote:

Having no funding was a huge advantage for me.

A year after I started CD Baby, the dot-com boom happened. Anyone with a little hot air and a vague plan was given millions of dollars by investors. It was ridiculous. …

It’s counterintuitive, but the way to grow your business is to focus entirely on your existing customers. Just thrill them, and they’ll tell everyone.

苏格拉底式提问

一种神秘的提问。下面是实操的流程:

Clarifying your thinking and explaining the origins of your ideas (Why do I think this? What exactly do I think?

把想法像费曼教学法那样表达清楚,并说明想法的来源(什么是我真正想的源头问题)

Challenging assumptions (How do I know this is true? What if I thought the opposite?)

挑战这个想法(我怎麼知道這是真的?事实是否与之相反)

Looking for evidence (How can I back this up? What are the sources?)

找证据验证(我如何支持这一点?来源的可信度如何保证?)

Considering alternative perspectives (What might others think? How do I know I am correct?)

其他观点会有问题吗?

Examining consequences and implications (What if I am wrong? What are the consequences if I am?)

思考想法的正确与否带来的结果(如果我錯了怎麼辦?如果我錯了,後果是什麼?)

Questioning the original questions (Why did I think that? Was I correct? What conclusions can I draw from the reasoning process?)

对最初的问题再次提问。当时我為什麼這麼想?我正確嗎?從推理過程中我可以得到什麼結論?

苏格拉底式提问通常被认为是开启 FTP 的模板。但实际上很多人的思维模型都包含了 FTP。到底是 modify 原有模型,还是 insert 苏格拉底式提问到大脑,看个人。

还是没明白?

看看我和 gpt 的讨论吧。

所以我能这么理解吗? 第一性原理,是帮助一个人拆解原问题,得到一堆基本真理。这些基本真理并不能很好的指导具体做什么,而是让决策者始终记得要参照什么指标(基本真理的具现化就是指标,比如用户体验流畅的具现化是 xx 功能的响应速度< 1s。还有常说的高可用,高并发,高性能)。决策者还要不断实践验证,重新评估这些指标的权重,由于世界不断变化,以及具体产品的指标在不同阶段有不同的权重。最后不断逼近目标是吧

*GPT4:

是的,您的理解是正确的。第一性原理作为一种思维框架,它帮助我们抛开常规假设,深入到问题的核心,找到最基本的真理或事实。这些基本真理是我们对问题的深刻理解,并不直接告诉我们具体的行动计划,而是作为我们制定计划和决策时的基石。

将基本真理转化为具体指标和行动步骤的过程通常涉及:

  • 拆解:将复杂的问题拆解为更基本的组成部分。
  • 量化:定义能够衡量或反映这些基本真理的指标。
  • 实验:通过实践来测试这些指标是否能够有效地指导我们接近目标。
  • 评估:根据反馈和数据来评估这些指标和行动计划的有效性。
  • 迭代:基于评估结果不断调整指标和计划,以更好地适应变化。

在这个过程中,决策者需要不断地检验和调整,因为世界在变化,市场在变化,技术在进步,用户的需求也在变化。每一次迭代都应该使我们更接近于目标,同时也更深刻地理解那些基本真理如何适用于当前的环境和情境。

所以,第一性原理提供的是一个始终不变的参照框架,但具体实施时需要决策者的洞察力、灵活性和创新能力,以确保在不断变化的世界中做出最佳决策。

选择原问题,即是选择锚点。在考虑资源有限的情况下,一种现实的做法是选好锚点进行拆解。上手将锚点定在终极问题上不一定是好决策,等待你的可能是人脑难以处理、纠缠不清的参数集合。

Reference

First Principles: The Building Blocks of True Knowledge (fs.blog)

First Principles: Elon Musk on the Power of Thinking for Yourself (jamesclear.com)