Hacker News Reader

Comment by am17an | Hacker News Reader

The non-thinking version is the best writer by far. Excited for this one! They really cooked some different from other frontier labs.

View on HN

Interesting, I have the opposite impression. I want to like it because it's the biggest model I can run at home, but its punchy style and insistence on heavily structured output scream "tryhard AI." I was really hoping that this model would deviate from what I was seeing in their previous release.

what do you mean by "heavily structured output"? i find it generates the most natural-sounding output of any of the LLMs—cuts straight to the answer with natural sounding prose (except when sometimes it decides to use chat-gpt style output with its emoji headings for no reason). I've only used it on kimi.com though, wondering what you're seeing.

Yeah, by "structured" I mean how it wants to do ChatGPT-style output with headings and emoji and lists and stuff. And the punchy style of K2 0905 as shown in the fiction example in the linked article is what I really dislike. K2 Thinking's output in that example seems a lot more natural.

I'd be totally on board if cut straight to the answer with natural sounding prose, as you described, but for whatever reason that has not been my experience.

From what I've heard, Kimi K2 0905 was a major downgrade for writing.

So, when you hear people recommend Kimi K2 for writing, it's likely that they recommend the first release, 0711, and not the 0905 update.

Ohhh, thanks, that's really good to know. I'll have to give that one a shot.

Interesting. As others have noted, it has a cut straight to the point non-psychophantic style that I find exceptionally rich in detailey and impressive. But it sounds like you're saying an earlier version was even better.

Again, it's just what I've heard, but the way I've heard it described is: they must have fine tuned 0905 on way too many ChatGPT traces.

> I find it generates the most natural-sounding output of any of the LLMs

Curious, does it do as well/natural as claude 3.5/3.6 sonnet? That was imo the most "human" an AI has ever sounded. (Gemini 2.5 pro is a distant second, and chatgpt is way behind imo.)

Kimi K2 has a very good model feel. Was made with taste

Reply on news.ycombinator.com