News for hackers. Stuff that matters.
Re:Anthropic's original take home assignment open sourced by HarHarVeryFunny on Wednesday January 21, 2026 @10:00AM (#46706618)
I just threw this prompt at Gemini, and it seems (I haven't analyzed the problem to see if it is correct), to be able to extract a clear understanding of the problem, and a specification for the kernel.

"Can you "reverse engineer" what the kernel in this optimization exercise is actually doing - write a specification for it?

https://github.com/anthropics/original_performance_takehome"

Gemini says it's doing inference on a random forest - taking a batch of inputs, running each one through each decision tree, and for each input outputting the sum of these decision tree outputs - the accumulated evidence.

Re:Anthropic's original take home assignment open sourced by HarHarVeryFunny on Wednesday January 21, 2026 @02:19PM (#46710180)
So looking at the actual code (reference_kernel() in problem.py), this "random forest inference" is completely wrong!

It's doing some sort of binary tree traversal, but the hashing and wrap around looks weird - maybe just a made up task rather than any useful algorithm?

Re:Anthropic's original take home assignment open sourced by saagarjha on Wednesday January 21, 2026 @03:00PM (#46710763)
Yes, it’s made up.