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

Kimi K3-256k

kimi.com

Post reply on HN
Print view View original

41–50 of 172 posts

Re: Kimi K3-256k

#41

Post by _zoltan_ »

cyanydeez wrote: post #6
giancarlostoro wrote: post #4

Earlier quoted context omitted.

For me the sweet spot is somewhere under 500k depending on how extensive I want to get. You can build up a sizable effort project in half a million tokens with Claude, with Claude having all the context from ground 0 to wherever you're off at.

I'm always curious what you guys are working on; every git repo I've run a local model on and stick below <100k to increase speed seems effective enough to scope patches and changes.

I have a couple projects where the background research is easily over 500k without writing any code, after ultracode subagents synthesis.

Re: Kimi K3-256k

#42

Post by archildress »

periodjet wrote: post #34

Why are Anthropic and OpenAI even allowing their coding harness apps to be plugged into different model providers…? I’m surprised they haven’t figured out a way to clamp down on that by now.

From my view, as soon as they do that, they send people out the door to use Opencode instead - and once many people have a taste of trying every model via Openrouter, it's eye opening as to the possibilities.

Of course - Anthropic and OpenAI have an advantage in the amount they can subsidize the usage, but I think those days are waning.

Re: Kimi K3-256k

#43

Post by holoduke »

jeppebemad wrote: post #32
holoduke wrote: post #31

A bit of topic. But how likely is it that the US will restrict Chinese open weight models and also force Euro countries to do the same? I think it will be effective within 6 months. The US is having a hard time staying competitive.

I don’t know, but I do think that the days of the US “forcing” Euro countries to do anything, is over.

[flagged]

Re: Kimi K3-256k

#44

Post by smotched »

KronisLV wrote: post #14
cyanydeez wrote: post #6

Earlier quoted context omitted.

I'm always curious what you guys are working on; every git repo I've run a local model on and stick below <100k to increase speed seems effective enough to scope patches and changes.

My current Claude Code session has been going on for like 35 hours and has used up around 400 million tokens, thankfully almost all of those being cached (95-98%) - pretty typical for long form agentic work. First you spend like 2-3 hours working on a plan, once you have that you just tell the model to go and implement it, do adversarial sub-agent review loops before each commit and also make sure that all tooling an…

Once you have the plan you don't need to keep the 2hrs of research in the context (which is most of it) you can drop that plan into a file and start fresh for implementation.

Re: Kimi K3-256k

#47

Post by BoorishBears »

wren6991 wrote: post #39

This seems functionally similar to OpenAI having a step in pricing once you exceed a certain context length (also at 272k aka 2^18 aka 256k). Having a lot of active context increases the per-token cost (flops issued and bytes read per token out) so it makes sense to pass that cost on to users. I'm actually surprised it's implemented as a hard cutoff instead of a smooth gradient.

Not surprising it's a hard cutoff: they almost certainly have two infrastructure configurations for the two max sequence lengths

Fewer nodes dedicated to prefill per instance, and fewer nodes in total since you don't need to support a higher KV cache.

Disaggregated inference also means they can tune the balance of compute dedicated to prefill seperately from decode

Re: Kimi K3-256k

#48

Post by therein »

Alifatisk wrote: post #18
lukan wrote: post #11

Since Claude is the first time for me really, really out (TIL against my wished about https://status.claude.com/ ), I am now interested enough to see what else works. But ... when I click pricing, I see "Join a waitlist". Wtf? Are they really that good, so were totally surprised and overwhelmed by the requests, is this a marketing stunt, or do they just don't have the hardware being in china?

No, the waiting list is true. Kimi had become that popular. I was a subscriber of Kimi back when latest version was Kimi K2. Later I unsubscribed because I jumped over to GLM subscription (they had amazing deal). Now when I wanted to try out Kimi K3 to find out what the fuzz was all about, I couldn’t subscribe to them. I remember reading a post from Moonshot team about this, they are doing this because they are almos…

I wish I could get a Kimi subscription. I'd jump away from Anthropic in a heartbeat.

When they first announced, I created an account but didn't subscribe, so I am stuck on a waitlist now.

Re: Kimi K3-256k

#49

Post by jscott817 »

Can we assume that model performance at 90% of the 256k limit != 90% of 1M token limit?

Is this the exact same model just with less VRAM allocated for context window?

Re: Kimi K3-256k

#50

Post by dools »

Hopefully this helps reduce some of the pressure on their infrastructure. Their models have all become super dumb recently and their support are not addressing it. I have a hunch they’ve been serving a significant percentage of requests with quantised models.
Post reply on HN