陶哲轩博客写数学问题时,通常先把对象定义清楚,再给直觉、反例和证明轮廓。把「Nines of safety: a proposed unit of measurement of risk」改写成可阅读的中文笔记,重点是:问题在问什么、已知到哪一步、下一步最容易走偏在哪。原站广告、分享条和导航已去掉。

问题在问什么

In everyday usage, we rely heavily on percentages to quantify probabilities and proportions: we might say that a prediction is accurate or accurate, that there is a chance of dying from some disease, and so forth. However, for those without extensive mathematical training, it can sometimes be difficult to assess whether a given percentage amounts to a “good” or “bad” outcome, because this depends very much on the context of how the percentage is used. For instance:

Because of all the very different ways in which percentages could be used, I think it may make sense to propose an alternate system of units to measure one class of probabilities, namely the probabilities of avoiding some highly undesirable outcome, such as death, accident or illness. The units I propose are that of “ nines “, which are already commonly used to measure availability of some service or purity of a material, but can be equally used to measure the safety (i.e., l

已知结果和反例

Here is a conversion table between percentage rates of success (the safe outcome), failure (the unsafe outcome), and the number of nines of safety one has:

Thus, if one has no nines of safety whatsoever, one is guaranteed to fail; but each nine of safety one has reduces the failure rate by a factor of . In an ideal world, one would have infinitely many nines of safety against any risk, but in practice there are no guarantees against failure, and so one can only expect a finite amount of nines of safety in any given situation. Realistically, one should thus aim to have as many nines of safety as one can reasonably expect to have,

证明或构造的主线

Now to give some real-world examples of nines of safety. Using data for deaths in the US in 2019 (without attempting to account for factors such as age and gender), a random US citizen will have had the following amount of safety from dying from some selected causes in that year:

The safety of air travel is particularly remarkable: a given hour of flying in general aviation has a fatality rate of , or about nines of safety, while for the major carriers the fatality rate drops down to , or about nines of safety.

阅读时建议盯住的点

Of course, in 2020, COVID-19 deaths became significant. In this year in the US, the mortality rate for COVID-19 (as the underlying or contributing cause of death) was per , corresponding to nines of safety, which was less safe than all other causes of death except for heart disease and cancer. At this time of writing, data for all of 2021 is of course not yet available, but it seems likely that the safety level would be even lower for this year.

Some further illustrations of the concept of nines of safety:

值得单独记下的条目

  • (i) In a two-party election, an outcome of say to might be considered close, but to would probably be viewed as a convincing mandate, and to would likely be viewed as a landslide.
  • (ii) Similarly, if one were to poll an upcoming election, a poll of to would be too close to call, to would be an extremely favorable result for the candidate, and to would mean that it would be a major upset if the candidate lost the elect
  • success = one nine of safety
  • success = two nines of safety
  • success = three nines of safety
  • The ancient Roman punishment of decimation , by definition, provided exactly one nine of safety to each soldier being punished.
  • Rolling a on a -sided die is a risk that carries about nines of safety.
  • Rolling a double one (“ snake eyes “) from two six-sided dice carries about nines of safety.

阅读和落地时建议先做的 5 件事

  1. 用自己的语言重写定义和结论,不看原文能不能说清对象是什么。
  2. 找一个最小反例或边界情形,确认假设少一条会怎样。
  3. 把证明拆成可独立检验的引理,每步只保留一个新想法。
  4. 若涉及计算或形式化,先写可复现的小例子,再谈一般情形。
  5. 记下尚未解决的缺口:缺估计、缺构造,还是缺正确的范畴。

和智能体、形式化工具怎么接

龙虾PRO做 OpenClaw 落地时,数学笔记最有用的部分往往是「可检验的步骤」:定义、反例、引理边界。智能体适合帮忙展开计算和检索,不适合代替你决定哪条假设能扔。

效率龙虾 会带着下面这段开聊

按文章《「Nines of safety: a proposed unit of m…》把卡点收成可执行步骤:先做什么、别踩哪条、怎么验证。

用效率龙虾试这篇

本文侧重全链路风控方法论。落地时请用自身业务单据做回放验证,不要把示例阈值直接当生产策略。 相关:风控体检 · 方案资源

常见问题 FAQ

什么是AI智能系统?

「AI智能系统」可概括为:In everyday usage, we rely heavily on percentages to quantify probabilities and proportions: we might say that a prediction is accurate or accurate, that there is a chance of dying 本文从定义、方法与实践要点展开说明。

为什么要关注AI智能系统?

关注AI智能系统,是因为它直接影响效率、风险与可复制性。文中指出:In everyday usage, we rely heavily on percentages to quantify probabilities and proportions: we might say that a prediction is accurate or accurate, that there is a chance of dying from some disease, and so forth. However, for those without exten…

如何落地AI智能系统?有哪些关键步骤?

建议按以下路径推进AI智能系统:1) success = one nine of safety;2) success = two nines of safety;3) success = three nines of safety;4) The ancient Roman punishment of decimation , by definition, provided exactly on…;5) Rolling a on a -sided die is a risk that carries about nines of safety.。细节见正文对应章节。

AI智能系统适合哪些人或团队?

AI智能系统更适合:产品/技术负责人、运营与增长团队、需要落地智能体或自动化的中小团队、关注「AI智能系统」方向的读者。若你只需要单次聊天式问答,可先读概念;若要上生产,请重点看步骤、权限与风控相关段落。

关于「问题在问什么」,本文给出了什么结论?

在「问题在问什么」部分,要点是:ilities and proportions: we might say that a prediction is accurate or accurate, that there is a chance of dying from some disease, and so forth. However, for those without extensive mathematical training, it can sometim

关于「已知结果和反例」,本文给出了什么结论?

在「已知结果和反例」部分,要点是:aranteed to fail; but each nine of safety one has reduces the failure rate by a factor of . In an ideal world, one would have infinitely many nines of safety against any risk, but in practice there are no guarantees agai