Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Anthropic's original take home assignment open sourced

github.com

Post reply on HN
Print view View original

251–260 of 394 posts

Re: Anthropic's original take home assignment open sourced

#251

Post by mike_hearn »

owlbite wrote: post #247
mike_hearn wrote: post #143

Earlier quoted context omitted.

The question isn't clearly written down anywhere, that's why. Presumably actual candidates would have been given more info over the phone or email. Part of the "challenge" is reverse engineering their Python; unclear if that's intentional. If you look at the top of perf_takehome.py then there is a brief comment saying the challenge is to optimize a kernel. Kernel in GPU land means a program that computes on data in p…

I think calling VLIW "an adandoned design" is somewhat of an exaggeration, such architectures are pretty common for embedded audio processing.

Sure. I did mention DSPs. But how many people write code for DSPs?

Re: Anthropic's original take home assignment open sourced

#252

Post by lovich »

YetAnotherNick wrote: post #169
lovich wrote: post #152

Earlier quoted context omitted.

No fucking shit, I paraphrased Anthropic's comments as > do better than we have publicly admitted most of humanity can do, and we may deign to interview you If you think telling someone that after passing a test that 99.999% of humanity cannot pass, that they _may_ get an interview, you are being snarky/condescending.

So I like these public challenges, but as someone who set some public questions, ask any company who ran any public contest for their opinion. The pool is filled with scammers who either bought the solutions through sites like Chegg or sometimes even just stackoverflow.

Ok, so they have a reason to be condescending in your mind.

Does that change the fact that they are condescending?

Re: Anthropic's original take home assignment open sourced

#253

Post by sublimefire »

Did a bit of soul searching and manually optimised to 1087 but I give up. What is the number we are chasing here? IMO I would not join a company giving such a vague problem because you can feel really bad afterwards, especially if this does not open a door to the next stage of the interview. As an alternative we could all instead focus on a real kernel and improve it :)

Re: Anthropic's original take home assignment open sourced

#254

Post by trillic »

aiiotnoodle wrote: post #211
bjackman wrote: post #87

Earlier quoted context omitted.

Lately with Gemini CLI / Jules it doesn't seem like time spent is a good proxy for difficulty. It has a big problem with getting into loops of "I am preparing the response for the user. I am done. I will output the answer. I am confident. Etc etc". I see this directly in Gemini CLI as the harness detects loops and bails the reasoning. But I've also just occasionally seen it take 15m+ to do trivial stuff and I suspect…

I've noticed using antigravity and vscode, Gemini 3 pro often comes back with model too busy or something like that and basically 500s. Seems like capacity because it works a lot better late at night. I don't see the same with the claude models in antigravity.

Anecdotally, I notice better performance and output quality across most providers outside of 8a-5p ET.

Re: Anthropic's original take home assignment open sourced

#255

Post by fc417fc802 »

maccard wrote: post #204
forgotpwd16 wrote: post #150

Earlier quoted context omitted.

This is nice writeup. Thanks. Another commenter said will've taken them 2h just to sketch out ideas; sans LLMs will've taken me more than 2h just to collect all this info let alone start optimizing it.

I've not written a VM before, but the comments in perf_takehome.py and problem.py explain the basics of this. I gleaned about half of this comment in a few minutes of just skimming the code and reading the comments on the functions and classes. There's only 500 lines of code really (the rest is the benchmark framework).

Same thought. I doubt they provided additional explanation to candidates - it seems that basic code literacy within the relevant domain is one of the first things being tested.

On the whole I don't think I'd perform all that well on this task given a short time limit but it seems to me to be an extremely well designed task given the stated context. The reference kernel easily fits on a single screen and even the intrinsic version almost does. I think this task would do a good job filtering the people they don't want working for them (and it seems quite likely that I'm borderline or maybe worse by their metric).

Re: Anthropic's original take home assignment open sourced

#256

Post by fc417fc802 »

carschno wrote: post #157
mike_hearn wrote: post #143

Earlier quoted context omitted.

The question isn't clearly written down anywhere, that's why. Presumably actual candidates would have been given more info over the phone or email. Part of the "challenge" is reverse engineering their Python; unclear if that's intentional. If you look at the top of perf_takehome.py then there is a brief comment saying the challenge is to optimize a kernel. Kernel in GPU land means a program that computes on data in p…

On the one hand, this exercise probably reflects a realistic task. Daily engineering work comprises a lot of reverse engineering and debugging of messy code. On the other hand, this does not seem very suitable as an isolated assignment. The lack of code base-specific context has a lot of potential for frustration. I wonder what they really tested on the candidates, and whether this was what they wanted to filter for.

> The lack of code base-specific context has a lot of potential for frustration.

I think that's one of the intentional points. Being able to quickly understand what the provided source code is doing.

Re: Anthropic's original take home assignment open sourced

#257

Post by paxys »

game_the0ry wrote: post #243

> If you optimize below 1487 cycles, beating Claude Opus 4.5's best performance at launch, email us at performance-recruiting@anthropic.com with your code (and ideally a resume) so we can be appropriately impressed and perhaps discuss interviewing. This is an interesting way to recruit. Much better than standard 2 leetcode medium/hard questions in 45 mins.

This is simply to enter the recruiting pipeline. once you're in you will do the same leetcode interviews as everyone else.

Re: Anthropic's original take home assignment open sourced

#258

Post by epolanski »

lbreakjai wrote: post #70

I consider myself rather smart and good at what I do. It's nice to have a look at problems like these once in a while, to remind myself of how little I know, and how much closer I am to the average than to the top.

Computing is a very broad topic. Even Linus or Carmack have no skills or knowledge about countless topics that would be mundane to you.

It doesn't matter really, what matters is our ability to stare into the void of what we don't know and start making progress.

Our ability to process and master new topics is part of the job.

I'm sure you've done that countless times.

Re: Anthropic's original take home assignment open sourced

#260

Post by godelski »

giancarlostoro wrote: post #229
fny wrote: post #186

Earlier quoted context omitted.

It's because the higher up the stack you go, tools become more declarative and literate. Calling sort is far easier than understanding the algorithm for example.

> Calling sort is far easier than understanding the algorithm for example. This was one of my gripes in college, why am I implementing something if I just need to understand what it does? I'm going to use the built-in version anyway.

So you know which sort to call because there isn't a right answer for all cases.

And so you can write your own because you're probably going to want to sort data in a specific way. Sort doesn't mean in numerical increasing or decreasing order, it means whatever order you want. You're sorting far more often than you're calling the sort function.

Post reply on HN