Top all-time · #2389
Win Vector LLC
Personal blog · win-vector.com · on HN as jmountdataprogrammingscience
Win Vector LLC is a personal blog at win-vector.com about data, programming and science. Since 2008, 34 different Hacker News readers have linked it 447 times, most often “Automatic Differentiation with Scala (with example code)”. It is still writing: the last post was on 2026-10-27, and you can follow it by feed.
Advising, Consulting, Training About Win Vector LLC Win Vector LLC is a San Francisco based company specializing in data science. We work in a variety of industries, with organizations both large and small. Our Win Vector blog is followed by data scientists worldwide. Read More About Win Vector LLC
Most-linked posts?
- Automatic Differentiation with Scala (with example code)3 people · 5 mentions · first linked 2010-06-15
- Use standard deviation (not mad about MAD)2 people · 6 mentions · first linked 2014-01-19
- Efficient accumulation in R2 people · 4 mentions · first linked 2015-07-28
- Deming, Wald and Boyd: cutting through the fog of analytics2 people · 4 mentions · first linked 2010-04-20
- A Few Notes on how to Survive R2 people · 4 mentions · first linked 2009-09-30
- The History of "Hello World"2 people · 4 mentions · first linked 2010-04-16
- How to Read Sourav Chatterjee’s Basic Xicor Defenition2 people · 3 mentions · first linked 2021-12-26
- A randomized algorithm that fails with near certainty2 people · 3 mentions · first linked 2013-02-14
- The Simpler Derivation of Logistic Regression2 people · 3 mentions · first linked 2011-09-14
- Text as a "Market for Lemons"2 people · 2 mentions · first linked 2025-12-02
What Hacker News says?
Turns out to be a great queueing problem. Please check out my analysis of much simplified version of the random routing algorithm that fails with near certainty: http://www.win-vector.com/blog/2013/02/randomized-algorithms...
Comment linking /blog/2013/02/randomized-algorithms-can-have-bad-deterministic-consequences/
on “Heroku's Ugly Secret: The story of how the cloud-king turned its back on Rails”Submitted Kelly Can't Fail as a story · 393 points
HN discussionFor more fun, my commentary on leftpad code: http://www.win-vector.com/blog/2016/03/more-on-npm-leftpad/
Comment linking /blog/2016/03/more-on-npm-leftpad/
on “NPM and Left-Pad: Have We Forgotten How to Program?”Submitted I want flexible queries, not RAG as a story · 237 points
HN discussionAnd corporations like AT&T are themselves immune to having their own identities stolen (my notes: https://win-vector.com/2024/07/12/yet-another-way-corporatio... ). Corporate EINs (the US corporation equivalent to US social security numbers) and public. Knowing one doesn't let you commit identity theft and credit card against a corporation (unlike the case for people).
Comment linking /2024/07/12/yet-another-way-corporations-outrank-people/
on “AT&T says criminals stole phone records of 'nearly all' customers in data breach”Submitted A Personal Perspective on Machine Learning as a story · 78 points
HN discussionA-10 was a Boyd sponsored aircraft, a fun topic: http://www.win-vector.com/blog/2010/04/deming-wald-and-boyd-...
Comment linking /blog/2010/04/deming-wald-and-boyd-cutting-through-the-fog-of-analytics/
on “Dark spot under cockpit of A-10s”Submitted Machine Learning Model Homotopy as a story · 66 points
HN discussionLove Moon, here is my article on Gerty http://www.win-vector.com/blog/2011/07/gerty-a-character-in-...
Comment linking /blog/2011/07/gerty-a-character-in-duncan-jones-moon/
on “Moon”Submitted Solving Recurrence Relations as a story · 64 points
HN discussionjmount has an explanation elsewhere in this thread linking to https://win-vector.com/2021/12/26/how-to-read-sourav-chatter... which does a great job of explaining the intuition, but in a nutshell the normalization factor of 3 comes from the fact that if you select two random points between 0 and 1, the mean distance between will be 1/3 (which is pretty easy to write down and solve, boils down the the fact that a pyr…
Comment linking /2021/12/26/how-to-read-sourav-chatterjees-basic-xicor-defenition/
on “A New Coefficient of Correlation”Submitted “The Mythical Man Month” is still a good read as a story · 63 points
HN discussionI share some notes on reading/explaining the basic definition here: https://win-vector.com/2021/12/26/how-to-read-sourav-chatter...
Comment linking /2021/12/26/how-to-read-sourav-chatterjees-basic-xicor-defenition/
on “A New Coefficient of Correlation”Submitted Why I don’t like Dynamic Typing as a story · 60 points
HN discussionNumpy is basically lapack. You'd be hard pressed to replace that with something nearing its performance. For autodiff, I dunno, how about John Mount's explanation? http://www.win-vector.com/blog/2010/06/automatic-differentia...
Comment linking /blog/2010/06/automatic-differentiation-with-scala/
on “Swift: Google’s Bet on Differentiable Programming”Submitted R in a 64 bit world as a story · 43 points
HN discussionI've blogged a fun writeup of the math in the (unimportant and actually against Tesla) formal bias in evaluating a failure rate right after the first failure: http://www.win-vector.com/blog/2013/10/estimating-rates-from...
Comment linking /blog/2013/10/estimating-rates-from-a-single-occurrence-of-a-rare-event/
on “Model S Fire”Submitted Can a classifier that never says “yes” be useful? as a story · 36 points
HN discussionNifty example. Billionaires, trillion dollar budges, billion-view celebrities, fast CPUs, and large memories: all reasons I am done with 32 bit architectures (old article of mine, but only on large memories http://www.win-vector.com/blog/2012/09/i-am-done-with-32-bit... ).
Comment linking /blog/2012/09/i-am-done-with-32-bit-machines/
on “Gangnam Style breaks YouTube viewer count”Submitted Solving 100 Bushels Using Matrix Factorization as a story · 33 points
HN discussionA nice complement to the command line "open" command is adding a shell launcher to OSX finder. I have some instructions how to do this here: http://www.win-vector.com/blog/2012/05/enhance-osx-finder/
Comment linking /blog/2012/05/enhance-osx-finder/
on “OS X Command Line Utilities”Submitted The Geometry of Classifiers as a story · 31 points
HN discussionI've added a follow-up note on the case of discrete stakes here: https://win-vector.com/2024/12/21/kelly-betting-with-discret... . It is known there is a dynamic programming strategy that guarantees a return of $8.08 on a $1 bet. Simple rounding of the Kelly strategy does not achieve this.
Comment linking /2024/12/21/kelly-betting-with-discrete-stakes/
on “Kelly Can't Fail”Submitted Let's try to motivate schemes as a story · 29 points
HN discussionI agree http://www.win-vector.com/blog/2010/02/postels-law-not-sure-... . Correct code remains correct under various compositions and transformations (that may happen in the future). Code that is working only due to pity often does not have this property. Some Netflix style chaos-monkey that turns on and off strictness during testing would be cool.
Comment linking /blog/2010/02/postels-law-not-sure-who-to-be-angry-with/
on “Post Mortem: A single whitespace character”Submitted A deeper theory of testing as a story · 28 points
HN discussionWow, that is really ugly semantics. Here are some notes of mine on how hard R works to avoid exposing this sort of aliasing/mutability issue to the user: http://www.win-vector.com/blog/2014/04/you-dont-need-to-unde...
Comment linking /blog/2014/04/you-dont-need-to-understand-pointers-to-program-using-r/
on “Anti-Patterns in Python Programming”Submitted My Opinion on “5” == 5 as a story · 27 points
HN discussionI have some notes on the Computational Learning Theory view of decision tree fitting (and over fitting) here: http://www.win-vector.com/blog/2017/01/why-do-decision-trees...
Comment linking /blog/2017/01/why-do-decision-trees-work/
on “Introduction to Decision Tree Learning”Submitted Factors are not first-class citizens in R as a story · 27 points
HN discussion
