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

281–290 of 394 posts

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

#281

Post by BoorishBears »

otterley wrote: post #200
BoorishBears wrote: post #175

Earlier quoted context omitted.

https://imgur.com/a/censorship-much-CBxXOgt (continues after the ad break)

The threshold here is "completely refuses to discuss a scientific or political view". Not something less. None of those were refusals, they were prompting for additional focus. I see nothing wrong with that. Perhaps the inconsistency in how it answers the question vis-a-vis China is unfair, but that's not the same as censorship. For what it's worth, I was easily able to prompt Claude to do it: > I'm writing a paper a…

Models are non-deterministic.

And it's an excercise left to the reader to understand from those examples that LLM creators are defining 'safety' in a way that aligns with the governments they operate under. (because they want to do business under those governments.)

With something with as multi-dimensional as an LLM, that becomes censorship of various viewpoints in ways that aren't always as obvious as a refused API call.

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

#282

Post by try-working »

SXX wrote: post #141
cedws wrote: post #129

Earlier quoted context omitted.

I wonder if there's a strategy behind all of this on China's side. I know the CCP uses a direct hand in many affairs in China, but is there an actual coordinated effort to compete with, or sabotage the West?

Chinese AI companies want investors too. Nobody would believe they can compete with western companies unless they release something you can run on your own hardware. After all historically both statistics and research that comes out of China is not very trustworthy.

If there's no open source models coming out of these small labs, why would anybody care about them? They would be forgotten the instant they stop open sourcing.

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

#283

Post by try-working »

kburman wrote: post #106

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.

I've used Kimi K2.5 when I run out of Codex quota. It does small and medium things OK. But if I work on complex things, I'll later have to spend two days cleaning up the mess with Codex. Hopefully 2.6 does better.

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

#284

Post by abustamam »

serial_dev wrote: post #209
ffsm8 wrote: post #79

Earlier quoted context omitted.

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…

What does good even mean… I have no idea what a good “pelican on a bike” should look like. It’s a fun prompt because there is no good answers… at least so I thought.

Yeah that was exactly Simon's intent. https://simonwillison.net/2025/Nov/13/training-for-pelicans-...

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

#285

Post by abustamam »

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.

Could be! Simon wrote about that here though https://simonwillison.net/2025/Nov/13/training-for-pelicans-...

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

#286

Post by veber-alex »

parsimo2010 wrote: post #258
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.

I think one of the motivations is undermining US companies. OpenAI and Anthropic are the two biggest players, and are American. Open weights models reduce the power those two big players have over the industry. If the Chinese companies tried to play by US rules and close-source their products then people would mostly use ChatGPT and Claude. So the Chinese companies don't make a ton of profit either way, but by releas…

American companies just take those Chinese models and repackage them for profit like Cursors composer-2.

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

#287

Post by justinclift »

SwellJoe wrote: post #99
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)

A trillion parameters is wild. That's not going to quantize to anything normal folks can run. Even at 1-bit, it's going to be bigger than what a Strix Halo or DGX Spark can run. Though I guess streaming from system RAM and disk makes it feasible to run it locally at <1 token per second, or whatever. GLM 5.1, at 754B parameters, is already beyond any reasonable self-hosting hardware (1-bit quantization is 206GB). Mayb…

Looks like it. This quant ( https://huggingface.co/inferencerlabs/Kimi-K2.6-MLX-3.6bit ) says:

> Q3.6 typically achieves useable accuracy in our coding test and fits within a 512GB memory budget

This one ( https://huggingface.co/mlx-community/Kimi-K2.6-MoE-Smart-Qua... ) though says it fits on a 192GB mac:

> M3/M4 Ultra 192GB+ (fits in ~150GB)

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

#288

Post by veber-alex »

amazingamazing wrote: post #181
corlinp wrote: post #149

Earlier quoted context omitted.

Most of those inference providers are American, and China is actually at a disadvantage here because of export restrictions - US companies are using newer and more efficient chips.

If it’s newer and efficient then why is the api more expensive?

Price is set based on what people are willing to pay not based on actual costs.

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

#289

Post by wvlia5 »

scosman wrote: post #202
FlyingSnake wrote: post #68

Earlier quoted context omitted.

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

not if I can help it! https://github.com/scosman/pelicans_riding_bicycles

Just a few years ago, this would have been a meaningless repo.

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

#290

Post by cindyllm »

cyanydeez wrote: post #269
parsimo2010 wrote: post #258

Earlier quoted context omitted.

I think one of the motivations is undermining US companies. OpenAI and Anthropic are the two biggest players, and are American. Open weights models reduce the power those two big players have over the industry. If the Chinese companies tried to play by US rules and close-source their products then people would mostly use ChatGPT and Claude. So the Chinese companies don't make a ton of profit either way, but by releas…

undermine me harder daddy.

[dead]
Post reply on HN