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

Re: Anthropic's original take home assignment open sourced

#171

Post by psb217 » Wed, Jan 21, 2026, 10:56 AM UTC

saagarjha wrote: post #134

wiz21c wrote: post #121

Earlier quoted context omitted.

I was in the demoscene long ago and that kind of optimisation is definitely in the ballpark of what we did: optimize algorithm down to machine code level (and additionally, cheat like hell to make you believe we ran the algorithm for real :-)). But to be honest, I wonder what algorithm they implement. I have read the code for 2 minutes, and it sound like random forest prediction. Anyone knows what the code does ?

It’s some useless problem like a random tree walk or something like that, the actual algorithm is not particularly important to the problem

Yeah, I assume it was partly chosen since the problem structure provides some convenient hooks for selectively introducing subtle and less subtle inefficiencies in the baseline algorithm that match common optimization patterns.

Re: Anthropic's original take home assignment open sourced

#172

Post by measurablefunc » Wed, Jan 21, 2026, 10:57 AM UTC

saagarjha wrote: post #138

measurablefunc wrote: post #116

Earlier quoted context omitted.

The task is ill-defined.

You make it faster

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.

Re: Anthropic's original take home assignment open sourced

#173

Post by bsder » Wed, Jan 21, 2026, 11:00 AM UTC

fergie wrote: post #96

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.

I'm 30 years in, and literally don't understand the question.

Since it's a CPU, you start with the idea that there is an ALU and spiral outward from that. That gives you something concrete to wrap your head around while you climb up the abstraction levels.

However, when I hit "scratch_write" and it wasn't in the Machine class and it wasn't coming from some Decorator and it was getting defined and deleted by a member function ... I stopped. That's paying lip service to the variable typing that is scattered around and actively hampers even basic IDE usage. Probably the typing was added by AI/LLM after the fact, and it missed that unusual usage. The Python convention used to be that those kinds of variables got declared as "_scratch_write" with a leading underscore to flag that they were "private/internal".

That was the gigantic red "We write shitty code" signal or worse "We don't care about wasting your time" signal. Human review should have flagged that.

Shame. I was kinda looking forward to the technical problem, but I'm not going to spend a bunch of time using grep to untangle garbage code to get at it.

I suspect everything would actually be much clearer if you wrote it in SystemVerilog and tested with Cocotb. Let's see if their LLMs can handle that porting job. HAH!

Re: Anthropic's original take home assignment open sourced

#174

Post by sva_ » Wed, Jan 21, 2026, 11:01 AM UTC

bjackman wrote: post #87

pvalue005 wrote: post #27

I suspect this was released by Anthropic as a DDOS attack on other AI companies. I prompted 'how do we solve this challenge?' into gemini cli in a cloned repo and it's been running non-stop for 20 minutes :)

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 feel like sometimes it just loops those messages when it doesn't actually generate new tokens. But I might be wrong

Re: Anthropic's original take home assignment open sourced

#175

Post by chistev » Wed, Jan 21, 2026, 11:03 AM 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.

What we know is a drop, what we don't know is an ocean.

Re: Anthropic's original take home assignment open sourced

#176

Post by mangatmodi » Wed, Jan 21, 2026, 11:04 AM 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.

Smart is different than the knowledge. If you learn about these concepts andwork on these problems, then you will be able to solve them.

It's not about you being average, just a different knowledge set.

Re: Anthropic's original take home assignment open sourced

#177

Post by matthews3 » Wed, Jan 21, 2026, 11:07 AM UTC

mrklol wrote: post #118

petters wrote: post #71

Earlier quoted context omitted.

And the answer to the obvious follow-up question is...?

Milk before cereals

Milk, then cereal, then bowl!

Re: Anthropic's original take home assignment open sourced

#178

Post by mixel » Wed, Jan 21, 2026, 11:13 AM UTC

bjackman wrote: post #87

pvalue005 wrote: post #27

I suspect this was released by Anthropic as a DDOS attack on other AI companies. I prompted 'how do we solve this challenge?' into gemini cli in a cloned repo and it's been running non-stop for 20 minutes :)

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 saw this too. Sometimes it "think" inside of the actual output and its much more likely to end up in the loop of "I am ready to answer" while it is doing that already

Re: Anthropic's original take home assignment open sourced

#179

Post by KeplerBoy » Wed, Jan 21, 2026, 11:13 AM UTC

measurablefunc wrote: post #133

saagarjha wrote: post #130

Earlier quoted context omitted.

Well, they read your code in the actual hiring loop.

My point still stands. I don't know what the LLM is doing so my guess is it's cheating unless there is evidence to the contrary.

Well that's certainly a challenge when you use LLMs for this test driven style of programming.

Re: Anthropic's original take home assignment open sourced

#180

Post by abra0 » Wed, Jan 21, 2026, 11:14 AM UTC

This is a really fun problem! I suggest anyone who likes optimization in a very broad sense to try their hand at it. Might be the most fun I've had while interviewing. I had to spend a week-worth of evenings on it to fully scratch the itch, and I managed to get 1112 cycles. But that was mostly manual, before the current crop of agentic models (clopus 4.5, gpt5.2). I wonder how far you can RalphWiggum it!