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

Tested Kimi K3 for Coding

dotnetperls.com

Post reply on HN
Print view View original

1–10 of 11 posts

Re: Tested Kimi K3 for Coding

#2

Post by garciasn »

Saving you a click:

> I decided to try it out and see if it could optimize my Rust program.

> Kimi K3 had 2 recommendations, and I decided to have it pursue the SWAR optimization—SIMD Within a Register. With SWAR, a single 64-bit value is treated as 8 eight-bit values—so we can handle 8 u8 values (single-byte) at once.

> Kimi K3 took about 15 minutes for the task, and it completed it perfectly. I found the optimization sped up the program by 2%.

> It cost about $1 for the tokens on OpenRouter.

Re: Tested Kimi K3 for Coding

#3

Post by akmarinov »

garciasn wrote: post #2

Saving you a click: > I decided to try it out and see if it could optimize my Rust program. > Kimi K3 had 2 recommendations, and I decided to have it pursue the SWAR optimization—SIMD Within a Register. With SWAR, a single 64-bit value is treated as 8 eight-bit values—so we can handle 8 u8 values (single-byte) at once. > Kimi K3 took about 15 minutes for the task, and it completed it perfectly. I found the optimizati…

Yeah that was a short article

Re: Tested Kimi K3 for Coding

#4

Post by cromka »

garciasn wrote: post #2

Saving you a click: > I decided to try it out and see if it could optimize my Rust program. > Kimi K3 had 2 recommendations, and I decided to have it pursue the SWAR optimization—SIMD Within a Register. With SWAR, a single 64-bit value is treated as 8 eight-bit values—so we can handle 8 u8 values (single-byte) at once. > Kimi K3 took about 15 minutes for the task, and it completed it perfectly. I found the optimizati…

Question is whether other models would offer same optimization or was it exclusive to K3? Would have been much more interesting write-up.

Re: Tested Kimi K3 for Coding

#6

Post by enraged_camel »

codemog wrote: post #5

Should have given the other frontier models a chance too? What if Fable or GPT-5.6 would have found a 30% speed up? Not like a sample size of one means much though.

Yeah, I'm not sure what the purpose of this article is. I don't have a lot of experience with Rust, but I think this is the type of task even Opus 4.5 could do.

Re: Tested Kimi K3 for Coding

#8

Post by arikrahman »

garciasn wrote: post #2

Saving you a click: > I decided to try it out and see if it could optimize my Rust program. > Kimi K3 had 2 recommendations, and I decided to have it pursue the SWAR optimization—SIMD Within a Register. With SWAR, a single 64-bit value is treated as 8 eight-bit values—so we can handle 8 u8 values (single-byte) at once. > Kimi K3 took about 15 minutes for the task, and it completed it perfectly. I found the optimizati…

$1 seem a lot, with a high cache hit rate it should be lower.
Post reply on HN