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

101–110 of 394 posts

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

#101

Post by SwellJoe »

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

"sufficient resources" is going to be a lot of resources. I doubt this will run on even something like a Strix Halo or DGX Spark, even at 1-bit quantization. You'll need a 256GB or 512GB Mac Studio, or a monster GPU situation, to run it locally, I think, though quantized versions aren't showing up yet, to be sure.

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

#102

Post by pheggs »

konart wrote: post #61
osti wrote: post #36

Earlier quoted context omitted.

Maybe open source == communism

But China is not communist event though the rulling party the word in its name.

what makes you think that china ever gave up its communist goals? I personally see that everything they do aims towards that goal. From the one child policy, the huge amounts of empty apartments they build, the stuff they produce for almost free, the fishing.. open sourcing the models perfectly fits that culture too, it's the means of production

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

#103

Post by nwienert »

ffsm8 wrote: post #79
FlyingSnake wrote: post #68

Earlier quoted context omitted.

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 prom…

The way I’ve come to think of LLM is that what the produce in a single reply even with thinking turned up, is akin to what you’d do in a single short session of work.

And so if you ask it to do something big it will do a very surface level implementation. But if you have it iterate many times, or give it small pieces each time, you’ll end up with something closer to what a human would do.

I imagine the pelican test but done in a harness that has the agents iterate 10+ times would be closer to what you’d expect, especially if a visual model was critiquing each time.

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

#104

Post by coder543 »

gpm wrote: post #75
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?

The description specifically says:

"Kimi-K2.6 adopts the same native int4 quantization method as Kimi-K2-Thinking."

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

#105

Post by atemerev »

sigmoid10 wrote: post #98
culi wrote: post #52

Earlier quoted context omitted.

All great technological advancements have come through opening up technology. Just look at your iPhone. GPS, the internet, AI voice assistants, touchscreens, microprocessors, lithium-ion batteries, etc all came from gov't research (I'm counting Bell Labs' gov't mandated monopoly + research funding as gov't) that was opened up for free instead of being locked behind a patent. Private companies will never open up a tec…

Still, you won't hear about Tiananmen square from this model. It flat out refuses to answer if pushed directly. It's also pretty wild how far they go to censor it during inference on the API, because it can easily access any withheld or missing info from training data via tool calls. It even starts happily writing an answer based on web search when asked indirectly, only to get culled completely once some censorship…

Only if you use Kimi API directly - the censorship is done externally. The model itself talks fine about Tiananmen, you can check on Openrouter. There might be less visible biases, though.

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

#106

Post by kburman »

Has anyone here used Kimi for actual work?

I tried it once, although it looks amazing on benchmarks, my experience was just okay-ish.

On the other hand, Qwen 3.6 is really good. It’s still not close to Opus, but it’s easily on par with Sonnet.

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

#107

Post by atemerev »

Aeolun wrote: post #94
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 good, but it’s not quite Claude level. And their API has constant capacity issues. Price/quality is absolutely bonkers though. I loaded $40 a few weeks/months ago and I haven’t even gone through half of it.

Why use China model API from China if there are many independent providers available via Openrouter?

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

#108

Post by antirez »

Here I analyze the same linenoise PR with Kimi K2.6, Opus, GPT. https://www.youtube.com/watch?v=pJ11diFOjqo

Unfortunately the generation of the English audio track is work in progress and takes a few hours, but the subtitles can already be translated from Italian to English.

TLDR: It works well for the use case I tested it against. Will do more testing in the future.

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

#109

Post by lambda »

hn8726 wrote: post #92
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...

[flagged]

It's a lighthearted, fun, visual benchmark that's not part of the standard benchmarks; and at least traditionally, it was not something that the labs trained on so it was something of a measure of how well the intelligence of the model generalized. Part of the idea of LLMs is that they pick up general knowledge and reasoning ability, beyond any tasks that they are specifically trained for, from the vast quantity of data that they are trained on.

Of course, a while back there was a Gemini release that I believe specifically called out their ability to produce SVGs, for illustration and diagramming purposes. So it's not longer necessarily the case that the labs aren't training on generating SVGs, and in fact, there's a good chance that even if they're not doing so explicitly, the RLVR process might be generating tasks like that as there is more and more focus on frontend and design in the LLM space. So while they might not be specifically training for a pelican riding a bicycle, they may actually be training on SVG diagram quality.

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

#110

Post by atemerev »

fragmede wrote: post #90
amazingamazing wrote: post #13

Earlier quoted context omitted.

The psyop continues. Mythos until it’s released is vaporware. Notice how you can try kimi 2.6. Where is the same for mythos?

It's been released to "select partners".

Yeah, Crowdstrike among them. Clearly experts in this "security" thing, given what happened during the last incident...
Post reply on HN