> "I'd fail an interview candidate that suggested adding 1 each time for subsequent prime testing"
Congratulations! You must be that arrogant guy everybody hates interviewing with, the one with the superiority complex.
How about instead of just failing people over literally nothing (wasting everybody's time and money) - just ask the candidate whether they could somehow reduce the search space by utilizing the properties of a prime number?
Are we including it just to poke the bear? Prime numbers are typically defined as numbers with no positive divisors other than one and the number in question.
Well, I’m questioning it… not that it really matters.
-1, 0, and 1 are no good.
Two divisors for positive integer X:
1, X
I recently demonstrated GPT-4 via by having it explain phases of matter metaphorically with animals. Though impressive, it points to loose abstraction being more in range than firm abstraction. Let’s get that model a python interpreter and see how far we can take this party. Until then, I’m going to stick to explaining concepts.
————- included here for fun
Alright! Let's dive into the wild world of matter using some animal friends as examples:
1. *Solids* - Think of solids like a herd of elephants standing closely together. The elephants are packed in tight, barely moving, just maybe swaying a bit. They're sturdy and strong, just like solid things in our world. This is because the particles in a solid don't move around much; they just vibrate in place.
2. *Liquids* - Imagine a school of fish swimming in a pond. They're free to move around, weaving in and out, but they still stay pretty close to each other. They aren't packed as tightly as our elephant friends, but they aren't completely free either. This is like liquids: the particles are close, but they can move around and flow, just like water in a glass.
3. *Gases* - Now, picture a flock of birds soaring in the sky, free to fly in all directions. These birds aren't sticking close to one another; they're spread out, enjoying the vast space of the sky. In gases, the particles are like these birds, very spread out and moving all over the place.
4. *Plasma* - Think of plasma like dragons (I know they're mythical, but bear with me). These dragons breathe fire, and that fire is so hot and energetic that it can change the way things behave. Plasma is like that – it's gas that's become so hot that the particles are super energized and can even glow, like neon lights.
5. *Bose-Einstein Condensate (BEC)* - This one's a bit trickier, but imagine penguins in Antarctica. They huddle closely together to keep warm. BEC is like the coldest group of particles ever, where they start acting in strange, uniform ways, almost like one giant super-particle. It's like all the penguins moving together as one.
So, next time you think of matter, just remember our animal friends: the sturdy elephants, the flowing fish, the free-flying birds, the fiery dragons, and the huddled penguins!
Again, 1 fits, because it has two divisors: 1, and 1. You never said X != 1, nor does the definition upthread.
This isn't a silly gotcha, these things matter in math. For instance, when solving a quadratic equation, allowing for the solutions to be equal lets you avoid special-casing your understanding - instead of memorizing when the equation has zero, one or two solutions, you just learn it has two or zero (real) solutions, and the two solutions are allowed to be equal.
It's perfectly reasonable understanding. Inequality isn't a natural implicit assumption. E.g. if I say you have two variables:
int a;
int b;
I doubt you'd be insisting that `a != b` at all times.
No. In the set of integers, 1 is not two divisors if repeated. It is one divisor.
An element to set relationship is that element A is or is not in set B. So, if the set of divisors only contains 1, there is only one divisor. If 1 and 1 made two divisors, 1 and 1 and 1 and… would make infinite divisors, rendering the concept of counting divisors (i.e., the cardinal number of the set of divisors) meaningless.
M is a divisor of N if it is a number that divides N without a remainder. While divisors can be negative, they are conventionally limited to non-negative integers in primality and factoring.
If you’d wanted to dig in on negative vs. positive divisors, that quickly provides an avenue for clearer formality, but piling on 1 and saying it’s not a silly gotcha is pretty fruitless. And please don’t bother to say “you didn’t say it has only two divisors”, as that would, again, be a silly argument.
So wind back and really formalize the definition if you want: A prime number is a natural number with only two divisors in the set of natural numbers, 1 and itself.
While set theory is axiomatic, it’s not practical for me (or anyone else) to explain conventional foundations to avoid someone feeling like they need to wiggle out of a prior bad argument.
Just say “ah, okay” or stop replying and move on. Feel free to read up in Wikipedia or any other texts (or ping me privately if you’d like to discuss further), but this thread isn’t looking like it’s going to meaningfully contribute to the broader discussion. Accordingly, I’ll leave it here unless something meaningful comes up.
Downvoting this is not enough. I'd pay $5 (reddit style) to have this properly killfiled if HN allowed for that. Besides, not "everybody hates them, only those inmature enough to still need intellectual babysitting.
Finally we meet the lifeless drone that everybody complains about in the interviews.
My suggestion for your next interview: decide to hire them just based on their leetcode score, but invite to the interview just to flex that you're still better at puzzle solving :-D
So I take it you typically produce fully optimized, thoughtful, and correct code on the first iteration while being actively judged by a stranger, yes?
I assume you meant that you should add 2? If yes, that's such a mind boggling basic thing to do that I agree with you, and it makes no sense that you're being crucified.
Probably because there's significant overlap in the Venn diagram of people with years experience who professionally develop products that generate $millions in wealth/value, and people who would fail that interview.
Or we have worked with junior developers who have really grown and flourished under our care, who would never have gotten that chance with such insane Draconian judgements.
It's such an obvious "GOTCHA!!" setting someone up for failure.
The way it's framed is very cringy because it signals that they don't care in their interviews about determining how objectively effective a software developer is.
I don't get it. This is an extremely basic fact that most people can figure out after thinking about primes for a minute. Maybe if you ask for "what's an easy optimisation here?" This would make the candidate think more closely about invariants that their code should hold, which in itself is a very valuable skill.
Because I know enough not to write prime testing code that resemble anything like that loop to have to care about reducing its search space. If you actually want to test my knowledge about prime number, you can ask and I will tell you about using some probabilistic choice instead, and that I know fast deterministic one might exist, but I am not up to date on the state of the art.
If I have to write the loop above, I am assuming it is the Fizzbuzz equivalent of your company to show that I know how to write a while loop. I am not thinking about reducing the search space because I am writing the code semi-unconscious and frankly just want to get to the next question.
Same. Also, if I'm suspecting it's a "can they into loops" fizzbuzz test, I'd be wary of reducing the search space for the simple reason that it makes the code slightly more complex, introducing a chance to make e.g. off-by-one error, which would lose me points if the reviewer has the kind of "pedntic over irrelevant things" attitude this subthread is criticizing.
I've done that (maybe it was fizzbuzz, now that I'm thinking about it) and boy howdy does that get the people you're interviewing with agitated. Saying "I'm interviewing for a architect level container orchestration position. If I'm reinventing the wheel writing algorithms, something is terribly wrong" shuts them up, but doesn't make them any happier.
what does and container orchestration architect do ? Something like this cluster should use envoy and Prometheus. The new clusters rate isn’t usually high enough for the stack to change.
Real question I love these non conventional (swe, sre, pm, manager ) roles in tech
> I'd fail an interview candidate that suggested adding 1 each time for subsequent prime testing
The problem a team that always seeks the optimal solution is that never they get shit done. And that’s rarely optimal in a business context. Your view does not strike me to be nearly as arrogant as it is short-sighted.
I think on a team of one I want the guy who gets it done without thinking. On a team of two I want a guy that’s somewhere in the middle. And on a team of three, that’s when I want my optimiser. Because in the time that guy number 3 has written let’s say 3 files of optimal code, guy number 10 files of not optimal code. And you rarely need guy number 3 to fix all ten, you just need him to fix the one or two files that actually matter.
Clients rarely ask “is this optimal?”. But they always ask “is this done?”.
All three developers have different approaches. All three are assets.
I think on some level then you’re making the same mistake that we could say the “just add one guy” made if your comment is honest- not factoring in (his) speed.
I think code readability, rather than code optimisation is far more important thing to get hung up on in an interview (and is, I must remind some of you, not to be confused with conciseness). And you can see this in the end result. But if you’re following along and the interviewee already knows you know what’s going on because of that, you can see it in smaller ways- it could be as simple as going back and changing a variable name such as open (maybe a function?) to isOpen (almost always a Boolean value).
I think most of us are in this position pretty often where we’re writing and figuring out something at the same time, maybe we just see if it works first and don’t give a name much thought or maybe we change the actual value or type of a variable in the process and the variable name becomes ambiguous. I’d look for small indicators that shoe me that this person is considering readability. But I still don’t necessarily expect it to be as readable as it would be in a more natural setting I mean I think 90% of these sorts of things start off with the person saying “I swear I can type” within the first five minutes of being watched- if they get flustered while being watched that it effects their typing, it certainly also effects their coding as well.
You'd reject a candidate that is willing and legally able to work for free while also cloning themselves so they can pair program with every one of your employees at once?
Having "extremely basic understanding" of prime numbers immediately at one's command is important for approximately 0% of software engineering jobs. If you instant-fail a candidate for this, it says a lot more about you and your organization than the candidate.
Approx 0% of devs need to know what the earth is, but from lots of interviews I've given I've found consistent correlation between lack of basic knowledge and lack of ability to solve many things. It was so strong we found it much more cost effective to cut people early that didn't know at least a few of some standard knowledge items.
This is some really good advice here.
It's always a good idea to throw out all candidates that can't immediately recall what the first theoretical result of the rest mass of a Higgs boson was in the first paper describing was. Basic knowledge like this just correlates so well with ability to make proper decisions in API architecture.
I'd also save time and money cutting people that read as poorly as you're demonstrating.
Try actually measuring basic knowledge with competency at programming before thinking your opinion is better than measured data. Peer reviewed research finds similar results [1].
And yes, we tested all this carefully before enacting it. Interviews cost time and money, so giving 100% on every candidate despite quick signals is a waste of time and money that would be better spent on other candidates. If you want the best outcome then you allocate scarce resources based on expected returns, not on unfounded beliefs.
You probably do not have a child of 7 years old because they do not know at that age what is a prime number.
Second, basic math still that you never or rarely use or with very large time between usage might get rusty. You may understand the concept but not find the optimal solution. The way you are responding here shows quite a lot about how you are short sighted by instant-failing someone with a single question instead of trying to asses the whole person as much as you can. On you side, you are wasting opportunity to have a great person that could be a key player in your team by bringing other set of skill on the table.
> You probably do not have a child of 7 years old because they do not know at that age what is a prime number.
it's part of the curriculum for children of this age where I grew up (I did check)
> The way you are responding here shows quite a lot about how you are short sighted by instant-failing someone with a single question instead of trying to asses the whole person as much as you can. On you side, you are wasting opportunity to have a great person that could be a key player in your team by bringing other set of skill on the table.
it may also be the case that I have more in depth knowledge about the roles that I've interviewed candidates for
most recently: hiring people to work for quants
not instantly knowing that even numbers (other than 2) are not prime is a very strong signal
You're not testing for "basic math skills" here. What you're testing for is more like "immediately retrieves an irrelevant math fact after many years of having no need to think about it."
Look, if you think this sort of thing allows you to identify great candidates, good for you. But in my experience, not only is this kind of practice stupid on its face, but it leads to engineering orgs packed with people who are good at memorizing trivia but terrible at solving real problems.
I think the key problem here is that is is a bad programming question. If you know anything about prime numbers then coming up with an answer is trivial. If you expect a more optimized solution, then you are really only gauging the interviewee’s understanding of prime numbers. So effectively the interview is more about mathematics than it is about programming or problem solving.
You happen to remember a particular piece of knowledge, so you project that expectation onto others. Theory of mind.
> yes, we expect professional software developers to have basic maths skills
Skill != knowledge. "What is a prime number" can be looked up and understood by any competent programmer in <5 minutes.
> "what is a prime number" is taught to 7 year olds, it's not vector calculus
Then it's reasonable to expect that an interviewee would be able to learn it as well, given the same resources. It does not however follow that an interviewee would inherently have that knowledge, just because 7 year olds are taught it.
Bottom line is, you're making too many assumptions about complete strangers.
If they know "prime number" is some technical term to look up. They might confuse it with amazon prime or anything else depending on context. You waste time explaining, they get indignant they are supposed to coding not do maths, complete mess.
I'm mad at myself now that it has eaten 15 minutes of my time trying to come up with the right optimization. What's the trick? 2, +1, and then +2 from there on seems obvious but once you get to 9 is it worth building a list of nonprimes to skip?
Well it doesn’t double the speed, since anything with a factor of 2 undergoes only one loop iteration inside is_prime. It basically just saves a function call
Exactly, multiples of 2 can't be a prime, so skipping this saves a function call (that itself only does one comparison), so it is a very simple and relatively obvious optimization. But actually every multiple of a number per definition cannot be a prime, you can't just change the step size, but there are some nifty tricks to approach the problem from a different angle.
Common approach is to use square roots, this reduces the runtime. Recommend checking out project euler if you like solving hard math-code-o(n)-puzzles.
I didn't want to cheat by looking on S.O. but thanks ;)
Yes it makes sense (in the GPT code) that you'd only go up to i * i ... although looking at pythonic while: statements is just gross to me in this context, it would feel a lot more readable to say, e.g. in PHP:
for ($i=2;$i<sqrt($n);) {
$i+=($i==2 ? 1 : 2); //although the first one should just be outside the loop
}
There's lots of more advanced optimizations, which would be an interesting avenue for discussion in an interview, but the drain dead algorithm would just use +2 instead of +1
