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

Kimi K2.6: Advancing open-source coding

kimi.com

Post reply on HN
Print view View original

71–80 of 394 posts

Re: Kimi K2.6: Advancing open-source coding

#71

Post by SwellJoe »

culi wrote: post #49
elfbargpt wrote: post #26

I've always been surprised Kimi doesn't get more attention than it does. It's always stood out to me in terms of creativity, quality... has been my favorite model for awhile (but I'm far from an authority)

It's also one of the few models that seem capable of drawing an SVG clock https://clocks.brianmoore.com/

Interesting that the best performers are all Chinese-made models (DeepSeek and Qwen also perform consistently well). I wonder if there's more focus on vision and illustration in their training, or if something else is leading to their clear lead on this one test.

Re: Kimi K2.6: Advancing open-source coding

#72

Post by gpm »

pbowyer wrote: post #45
esafak wrote: post #8

K2.5 was already pretty decent so I would try this. Starting at $15/month: https://www.kimi.com/membership/pricing edit: Note that you can run it yourself with sufficient resources (e.g., companies), or access it from other providers too: https://openrouter.ai/moonshotai/kimi-k2.6/providers

What's the privacy/data security like? I can't find that on that page. Edit: found it. > We may use your Content to operate, maintain, improve, and develop the Services, to comply with legal obligations, to enforce our policies, and to ensure security. You may opt out of allowing your Content to be used for model improvement and research purposes by contacting us at membership@moonshot.ai. We will honor your choice i…

> We will honor your choice in accordance with applicable law.

So in other words only if you can point to a local law which requires them to comply with the opt out?

Re: Kimi K2.6: Advancing open-source coding

#73

Post by johndough »

Banditoz wrote: post #30

If the benchmarks are private, how do we reproduce the results? I looked up the Humanity's Last Exam ( https://agi.safe.ai/ ) this model uses and I can't seem to access it.

You can request access here: https://huggingface.co/datasets/cais/hle

The test data is purposely difficult to access to reduce the chance of leaking it into the training dataset.

Re: Kimi K2.6: Advancing open-source coding

#74

Post by tadfisher »

osti wrote: post #36
game_the0ry wrote: post #27

There is some humor in the fact that china (of all countries) is pioneering possibly the world's most important tech via open source, while we (US) are doing the exact opposite.

Maybe open source == communism

Nah, open source means those who do the work own the result. It's supercapitalism.

Re: Kimi K2.6: Advancing open-source coding

#75

Post by gpm »

verdverm wrote: post #17

https://huggingface.co/moonshotai/Kimi-K2.6 Is this the same model? Unsloth quants: https://huggingface.co/unsloth/Kimi-K2.6-GGUF (work in progress, no gguf files yet, header message saying as much)

Huh, so the metadata says 1.1 trillion parameters, each 32 or 16 bits.

But the files are only roughly 640GB in size (~10GB * 64 files, slightly less in fact). Shouldn't they be closer to 2.2TB?

Re: Kimi K2.6: Advancing open-source coding

#77

Post by sergiotapia »

motoboi wrote: post #7
nickandbro wrote: post #3

Wow, if the benchmarks checkout with the vibes, this could almost be like a Deepseek moment with Chinese AI now being neck and neck with SOTA US lab made models

With the previous generation? Yes. With 10T mythos-level models? Not even close.

mythos is vaporware right now, what are you talking about?

Re: Kimi K2.6: Advancing open-source coding

#78

Post by mistercheph »

motoboi wrote: post #7
nickandbro wrote: post #3

Wow, if the benchmarks checkout with the vibes, this could almost be like a Deepseek moment with Chinese AI now being neck and neck with SOTA US lab made models

With the previous generation? Yes. With 10T mythos-level models? Not even close.

Mythos doesnt exist

Re: Kimi K2.6: Advancing open-source coding

#79

Post by ffsm8 »

FlyingSnake wrote: post #68
simonw wrote: post #53

Accessed via OpenRouter, this one decided to wrap the SVG pelican in HTML with controls for the animation speed: https://gisthost.github.io/?ecaad98efe0f747e27bc0e0ebc669e94... Transcript and HTML here: https://gist.github.com/simonw/ecaad98efe0f747e27bc0e0ebc669...

At this point drawing these Pelicans must be in the training data sets.

Clearly not.

I mean the prompt was succinct and clear, as always - and it still decided to hallucinate multiple features (animation + controls) beyond the prompt.

It'd also like to point out that to date no drawing was actually good from an actual quality perspective (as in comparative to what a decent designer would throw together)

Theyre always only "good" from the perspective of it being a one shot low effort prompt. Very little content for training purposes.

Post reply on HN