Anthropic's original take home assignment open sourced • Hacker News Board

Re: Anthropic's original take home assignment open sourced

#261

Post by alt227 » Wed, Jan 21, 2026, 4:06 PM UTC

paxys wrote: post #257

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.

You would hope that if you manage to beat their engineers best optimisations at launch, then you would leapfrog a certain amount of the initial stages.

Then again, this may just be a way to get free ideas at optimising their product from outside the box.

Re: Anthropic's original take home assignment open sourced

#262

Post by ontouchstart » Wed, Jan 21, 2026, 4:10 PM UTC

sublinear wrote: post #246

Onavo wrote: post #117

Earlier quoted context omitted.

If you ask an EE to debug react state management code without prior exposure they won't do too well either. But on the other hand they can easily pick up most of it after a week long crash course while training a performance engineer who can optimize code for a specific architecture would take months.

> they can easily pick up most of it after a week long crash course I have to disagree and question what you mean by "optimization". It's very easy to write web code that technically accomplishes a task, but does so poorly. This is the natural consequence of having so many options available. The vast majority of web devs with less than 5 years of experience simply don't understand plain javascript well enough. It's a…

Engineering is more or less about getting familiar with the proper tools and use them to solve specific problems: add new features, debugging, refactoring and optimizing.

And the tools themselves are built by other engineers and they need new features, debugging, optimization etc. It is turtles all the way down.

But each layer has its own jargons, conventions and unwritten hacks. That is where experience comes in. Once you get out off a rabbit hole or pothole, you are one step closer to becoming the “domain expert”. There is no short cut.

Re: Anthropic's original take home assignment open sourced

#263

Post by triyambakam » Wed, Jan 21, 2026, 4:16 PM UTC

pvalue005 wrote: post #85

bird0861 wrote: post #68

Earlier quoted context omitted.

Which Gemini model did you use? My experience since launch of G3Pro has been that it absolutely sucks dog crap through a coffee straw.

/model: Auto (Gemini 3) Let Gemini CLI decide the best model for the task: gemini-3-pro, gemini-3-flash After ~40 minutes, it got to: The final result is 2799 cycles, a 52x speedup over the baseline. I successfully implemented Register Residency, Loop Unrolling, and optimized Index Updates to achieve this, passing all correctness and baseline speedup tests. While I didn't beat the Opus benchmarks due to the complexit…

> grow some veggies and raise chickens.

Maybe Claude will be able to do that soon, too.

Re: Anthropic's original take home assignment open sourced

#264

Post by whateveracct » Wed, Jan 21, 2026, 4:19 PM UTC

saagarjha wrote: post #142

whateveracct wrote: post #30

Earlier quoted context omitted.

4 hours continuous or no? I can't imagine finding 4 hours of straight focus.

Continuous

damn that sucks

i guess that ensures you either hire the childless

or those with children who are fine with be not present for that long willingly (so they are probably gonna be job-obsessed enough)

or they are currently unemployed so they won't have an existing job as anchoring leverage

well played, anthropic

Re: Anthropic's original take home assignment open sourced

#265

Post by benlivengood » Wed, Jan 21, 2026, 4:43 PM UTC

alt227 wrote: post #261

paxys wrote: post #257

Earlier quoted context omitted.

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

You would hope that if you manage to beat their engineers best optimisations at launch, then you would leapfrog a certain amount of the initial stages. Then again, this may just be a way to get free ideas at optimising their product from outside the box.

One could use any number of LLMs on a take-home problem so in-person interviews are a must.

Re: Anthropic's original take home assignment open sourced

#266

Post by measurablefunc » Wed, Jan 21, 2026, 4:45 PM UTC

saagarjha wrote: post #197

measurablefunc wrote: post #172

Earlier quoted context omitted.

Fewer instructions doesn't mean it's faster. It can be faster but it's not guaranteed in general. Obvious counterexample is single threaded vs multi-threaded code. Single threaded code will have fewer instructions but won't necessarily be faster.

It does in this case; you can read the assignment to see that it is all single-threaded

I read it, you're mistaken.

Re: Anthropic's original take home assignment open sourced

#267

Post by measurablefunc » Wed, Jan 21, 2026, 4:46 PM UTC

saagarjha wrote: post #195

measurablefunc wrote: post #170

Earlier quoted context omitted.

Because it's a well know failure mode of neural networks & scalar valued optimization problems in general: https://www.nature.com/articles/s42256-020-00257-z

Again, you can just read the code

You're missing the point. There is no evidence to support their claims which means they are more than likely leaking the memory into the LLM prompt & it is cheating by simply loading constants into memory instead of computing anything. This is why formal specifications are used to constrain optimization. Without proof that the code is equivalent you might as well just load constants into memory & claim victory.

Re: Anthropic's original take home assignment open sourced

#268

Post by elzbardico » Wed, Jan 21, 2026, 4:51 PM UTC

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.

There's a big chance you're falling in a subtle form of imposter syndrome that manifests itself by largely over-estimating the average skill level.

But this is good. Staying humble makes you hungrier for learning.

Re: Anthropic's original take home assignment open sourced

#269

Post by measurablefunc » Wed, Jan 21, 2026, 4:53 PM UTC

red75prime wrote: post #191

measurablefunc wrote: post #170

Earlier quoted context omitted.

Because it's a well know failure mode of neural networks & scalar valued optimization problems in general: https://www.nature.com/articles/s42256-020-00257-z

And? Anthropic is not aware of this 2020 paper? The problem is not solvable?

Why are you asking me? Email & ask Anthropic.

Re: Anthropic's original take home assignment open sourced

#270

Post by yodsanklai » Wed, Jan 21, 2026, 4:55 PM UTC

Incipient wrote: post #61

>so we can be appropriately impressed and perhaps discuss interviewing. Something comes across really badly here for me. Some weird mix of bragging, mocking, with a hint of aloof. I feel these top end companies like the smell of their own farts and would be an insufferable place to work. This does nothing but reinforce it for some reason.

Thanks for noticing this. I got the same feeling when reading this. It may not sound like much, and it doesn't mean it's an insufferable place to work, but it's a hint it might be.

Rant: On a similar note, I recently saw a post on Linkedin from Mistral, where they were bragging to recruit candidates from very specific schools. That sounded very pretentious (and also an HR mistake on several levels IMHO).