I cleared this assignment but did not clear the follow up interview that was way easier than this. So I gave up on tech interviews in general, stayed where I was.
Anthropic's original take home assignment open sourced
291–300 of 394 posts
Re: Anthropic's original take home assignment open sourced
#292Earlier quoted context omitted.
As an interviewer, I ask the same problems because it makes it much easier to compare candidates.
How do you know if one candidate happened to see the problem on leetcode and memorized the solution versus one who struggled but figured it out slower?
It's very easy to tell, but it doesn't make much difference. The best candidates have seen the problems before and don't even try to hide it, they just propose their solution right away.
I try give positive feedback for candidates who didn't know the problem but could make good use of hints, or had the right approach. But unfortunately, it's difficult to pass a Leetcode interview if you haven't seen a similar problem to what is asked before. Most candidates I interview nowadays seem to know all questions.
That's what the company has decided so we have to go along. The positive side is that if you do your part, you have good chances of being hired, even if you disagree with the process.
Re: Anthropic's original take home assignment open sourced
#293I'm at 1137 with one hour with opus now...
Pipelined vectorized hash, speculation, static code for each stage, epilogues and prologues for each stage-to-stage...
I think I'm going to get sub 900 since i just realized i can in-parallel compute whether stage 5 of the hash is odd just by looking at bits 16 and 0 of stage 4 with less delay.....
Re: Anthropic's original take home assignment open sourced
#294> 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.
Is this a fact or an assumption?
Re: Anthropic's original take home assignment open sourced
#295Earlier quoted context omitted.
After a quick look this is can be seen as a low level GPU/TPU optimization problem where you have to consider the throughput and depth of different arithmetic pipelines. If you want to hire people who understand how to do that you unfortunately have to give them such a convoluted task and emulate the relevant parts of HW. (In reality this is probably more like TPU since it has scalar pipelines, but the optimization m…
This also shows that a performance engineer's job, even at Anthropic, is to be a glorified human compiler, who is often easily beaten by LLMs.
I think the job is to be one of the few that's better than LLMs.
Re: Anthropic's original take home assignment open sourced
#296Earlier quoted context omitted.
Fair enough, and there are clues in the comments too, but why not just provide the specification of the kernel (inputs and outputs) as part of the problem?
They do. They provide reference_kernel which shows the algorithm itself, build_mem_image which shows the data format you will be working with, and finally reference_kernel2 which implements said algorithm on said data format. They then provide you with a very naive implementation that runs on their (very simple) VLIW architecture that you are to optimize. If at the end of that someone is still lost I think it is safe…
Well, yes, they have a reference implementation as documentation, just as they have the simulator as documentation for the ISA ...
The problem is about pipelining memory loads and ALU operations, so why not just give clear documentatation and state the task rather than "here's a kernel - optimize it"? \_(ツ)_/
Re: Anthropic's original take home assignment open sourced
#297Earlier 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.
x86-64 SSE and AVX are also SIMD
Re: Anthropic's original take home assignment open sourced
#298I'm at 1137 with one hour with opus now... Pipelined vectorized hash, speculation, static code for each stage, epilogues and prologues for each stage-to-stage... I think I'm going to get sub 900 since i just realized i can in-parallel compute whether stage 5 of the hash is odd just by looking at bits 16 and 0 of stage 4 with less delay.....
How do you avoid the load bottleneck?
Re: Anthropic's original take home assignment open sourced
#299I'm at 1137 with one hour with opus now... Pipelined vectorized hash, speculation, static code for each stage, epilogues and prologues for each stage-to-stage... I think I'm going to get sub 900 since i just realized i can in-parallel compute whether stage 5 of the hash is odd just by looking at bits 16 and 0 of stage 4 with less delay.....
How do you avoid the load bottleneck?
take advantage of index collisions, optimizing round 0 and 11, speculative pre-loading, and the early branch predictor (which now I am doing looking at bits output at stage 3)
Re: Anthropic's original take home assignment open sourced
#300Earlier quoted context omitted.
I'm 30 years in, and literally don't understand the question.
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…
"Performance can be optimized by not using python."