AI 与机器学习joelgrus.com
用 TensorFlow 写 Fizz Buzz
Fizz Buzz in Tensorflow
2016 — 2018，它一次次回到首页
黑点是上首页（≥ 50 分）的那次投稿，空心点是没冲上去的投稿，点越大分数越高。
导读
Joel Grus 的博客文章：他扮演一位面试者，用 TensorFlow 搭建神经网络来"解决" FizzBuzz 问题——把本可用一行取模判断搞定的问题硬生生做成训练模型、调参、预测的机器学习项目。全文以面试对话形式展开，故意把简单问题复杂化，讽刺"凡是问题都上深度学习"的风气。
为什么经久不衰：它同时调侃了机器学习万能论和 FizzBuzz 面试题文化这两件事，十年来始终是 ML 圈自嘲与面试官吐槽的共享梗。
HN 评论精选
FizzBuzz 是筛掉简历注水者的高效电话面试题，而非侮辱资深程序员。
这篇文章整个是在嘲讽拿 FizzBuzz 考资深程序员，但我发现它其实是最好的电话面试题之一。真正的资深程序员 30 秒就写完了，我们继续往下聊；而那些简历上假装资深的人会卡住，我立刻就知道简历要么全是假的，要么前同事帮了他们太多。如果我真遇到文中这位候选人，看到他一堆 import 大概会笑出来，说"显然你觉得这题很傻"，然后解释我为什么问这题。
jedberg查看英文原文
This whole thing is making fun of asking fizz-buzz to a senior programmer, but yet I've found it to be one of the best phone screen questions possible. For someone who is truly a senior programmer, they knock it out in about 30 seconds and we move on. For the ones who pretend to be senior programmers on their resume, it trips them up and I know right away that their resume is either a pack of lies or their previous coworkers were helping them a lot more than they let on. If I had actually had this person, I would have probably laughed as soon as he did the imports, said, "clearly you think this is a silly question" and then explained why I ask that question. Hopefully we could have moved on from there.
从招聘方经验看，写不出 FizzBuzz 的"程序员"比想象中多得多。
我知道对真正有能力的程序员来说这题显得居高临下。但作为招过人的人，我见过太多拿着 CS 学位、学历也核实无误，却连 FizzBuzz 都写不出来的人。有次我好玩用在线协作编程工具，几个"在职程序员"四小时后还在做 FizzBuzz，我吃完午饭回来都忘了这回事，结果到下班发现他们还在做……
vpmpaul查看英文原文
I know people consider it condescending if they are actually a competent programmer. However as a person that has done hiring I can't tell you how many people have a CS degree that they supposedly attended school and passed(as in their credentials check out) but can't even do the FizzBuzz test. Once time for fun I used one of those online code collaboration tools. I had a couple of "programmers" that were still actively working on the Fizzbuzz question 4 hours later. I went to lunch and forgot about it after I came back until the end of the day and realized there were still people working....
反方观点：用 FizzBuzz 炫技显得傲慢，也不该假定候选人知道这道题。
如果这事真发生了，我从这场面试里得到的唯一信号就是：候选人是个自大的混蛋。不录用。不要预设候选人一定熟悉某道题，不管它多有名——也许他来自别的国家，也许他正从别的行业转过来。而且如果题目出得难一点，面试官大概又会说"这也太不现实了，实际工作根本用不上"。当然，我属于 HN 上少数喜欢编程题面试的人，所以我懂什么。
fatjokes查看英文原文
If this actually happened the only signal I would get from this interview is that the candidate is a egotistical asshole. No hire. - It's always good to not assume that the candidate is familiar with a given question, no matter how well known it may be. Maybe they're from a different country, maybe they're from a different industry altogether making a transition. - I bet if the question was difficult or complex the interviewer would say "omg that's not realistic, would never use this in real job". Then again, I'm also in the minority of HN users who like coding/problem solving interviews so what do I know.
作者本人实践过：真正照做会发现坑在激活函数之类的细节上，也说明它是个不错的 ML 教学示例。
很有意思。几个月前我在公司做过一次现场演示，卡在让模型准确率足够可用上，后来看到这篇文章才发现是我的激活函数有点问题。大多数人能理解 FizzBuzz，而用神经网络一步步把它搭出来，说明少量 ML 代码就能在不为问题显式编程的前提下解决它，是个不错的示例。
razodactyl查看英文原文
This was fun, I did a live demo at work a few months ago on this, got stuck on getting the model to predict with enough accuracy to be useful then came across this post, my activation function was slightly off. Most people understand Fizz Buzz, building up and solving the problem with a neural network shows that a bit of ML code can solve the problem without being programmed explicitly to do so, quite a good example.
历次讨论
同类还值得读
如何写一个拼写纠正器
How to Write a Spelling Corrector
Peter Norvig 用一个几十行的 Python 程序演示如何做拼写纠正：先用编辑距离（删除、插入、替换、换位）生成所有可能的候选词，再用从大量文本中统计出的词频概率，选出…
AI 与机器学习上首页 10 次 · 2007–2022norvig.com编辑精选面向黑客的概率编程与贝叶斯方法
Probabilistic Programming and Bayesian Methods for Hackers (2013)
《黑客的贝叶斯方法与概率编程》是一本开源的贝叶斯统计入门书，以 Python/PyMC 代码和交互式 Jupyter Notebook 为主线，强调“先实践、后数学”的学习路径，…
AI 与机器学习上首页 5 次 · 2013–2018camdavidsonpilon.github.io编辑精选神经网络黑客指南
Hacker's Guide to Neural Networks
Andrej Karpathy 写的神经网络入门教程，面向程序员，从最简单的表达式求导讲起，逐步推导出反向传播和梯度下降，最后引出神经网络。
AI 与机器学习上首页 4 次 · 2014–2019karpathy.github.io编辑精选神经网络能逼近任意函数的可视化证明
A visual proof that neural nets can approximate any function
这一章来自 Michael Nielsen 的在线书《Neural Networks and Deep Learning》，用 sigmoid 单元叠加成局部隆起/平滑阶跃的图示…
AI 与机器学习上首页 4 次 · 2014–2022neuralnetworksanddeeplearning.com编辑精选论乔姆斯基与统计学习的两种文化
On Chomsky and the Two Cultures of Statistical Learning
Norvig 回应 Chomsky 对统计语言模型批评的文章，围绕“统计学习能否解释语言”展开，比较生成与解释、少参数模型与 Shannon 式高参数统计模型。
AI 与机器学习上首页 4 次 · 2011–2025norvig.com编辑精选