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

Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

fireworks.ai

Post reply on HN
Print view View original

291–300 of 491 posts

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#291

Post by claytonjy »

ralusek wrote: post #36
nharada wrote: post #28

Is there something specifically with Kimi that's better here? As far as I know Kimi pricing is about the same as Sonnet 5 -- what happens if you use that model and Fable instead? Or Grok 4.5 which is even cheaper?

One benefit of an open source one is that you can, as a large corporation, run it "locally" within your own data center. Even fine tune it.

How big is this market, self-hosting a model that requires 64 GPUs, H100 or better, with good interconnects between nodes?

I suspect the overlap of those that can afford it, and those that have the talent to manage it, is a fairly thin slice of the Venn diagram. Even the large corps are gonna be getting it from the inference vendors, or more likely Bedrock and friends.

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#292

Post by pixlmint »

nxtfari wrote: post #253

If you haven’t been really running and testing these models yourself, they are all benchmaxxed. No matter how close they score to frontier on whatever metric, they always fall apart in real world tasks and their token efficiency is ridiculously bad. Fireworks has incredible incentive to make this claim in a headline, because Fireworks hosting K3 for you is pure profit for them, unlike when they host closed source mod…

didn't read the article, but just the title felt fishy because of course an inference provider wouldn't mind claiming to provide access to a mythos-class model. So far, GLM 5.2 is still my go-to, even at less than a third the parameter count compared to Kimi K3

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#293

Post by apatheticonion »

aftbit wrote: post #204
apatheticonion wrote: post #83

Earlier quoted context omitted.

For me, the only utility OpenRouter gives me is billing consolidation - I don't really need the routing capabilities because I use Bifrost for that. As a router, it's not very feature rich. For example I restricted the available models to the ones I want to use however the `/models` endpoint still lists all the models, making my LLM client list the 200+ models available on the service (even though they will throw an…

Can you configure Bifrost using entirely config files without the web interface? Can it run without a database or anything stateful? I'm using LiteLLM but it is not trivial to run.

You can configure it with just config files.

Database is optional, if you add one, you get advanced caching.

It's just a single executable.

    wget https://downloads.getmaxim.ai/bifrost/v1.6.5/linux/amd64/bifrost-http
    chmod +x bifrost-http
    ./bifrost-http

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#294

Post by kzrdude »

criley2 wrote: post #182
ronsor wrote: post #44

Earlier quoted context omitted.

Have you looked into OpenCode Zen or OpenCode Go? https://opencode.ai/zen

Zen is nice, but they require US hosting so they don't get new Chinese models right away. There is no Kimi K3. Go is nice for the ten minutes you can use it until your hit your cap.

Go is great if you prefer deepseek V4 flash. Then it's very hard to use up the allowance.

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#296

Post by orbital-decay »

maxloh wrote: post #233
abdullahkhalids wrote: post #212

I will accept a 5% drop in benchmarks for a model that talks to me like a human.

Yeah. I've found that Opus by default outputs something I call "Claude-lang." It consists of oversimplified, grammatically incomplete sentences that I find painful to read. Maybe it is something that is easy for it to read and write, but definitely not for humans. For example, Skim once now; refer back while reading Part II. \*Every bold technical term in Part II is defined here\* — treat these as a dictionary, not a…

That's an accidental CoT language leak, it might happen. If it does this consistently, something is up with your prompt

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#297

Post by throwaway277432 »

4b11b4 wrote: post #218
abdullahkhalids wrote: post #212

I will accept a 5% drop in benchmarks for a model that talks to me like a human.

I strictly prefer when models ignore any human quirks in my responses. Claude trying to be your friend, saying LOL to your jokes is ridiculous and frankly, harmful

Claude (Opus 4.8) recently told me:

>I’d ask you to drop the abuse; (...) if it continues I’ll end the conversation.

After I'd used a couple of expletives. And yes it will emit a token.

This is truly dystopian. It is NOT a person. What a response. I still cant believe it.

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#298

Post by ezst »

4b11b4 wrote: post #218
abdullahkhalids wrote: post #212

I will accept a 5% drop in benchmarks for a model that talks to me like a human.

I strictly prefer when models ignore any human quirks in my responses. Claude trying to be your friend, saying LOL to your jokes is ridiculous and frankly, harmful

Anthropomorphizing big matrices is how those "labs" managed to sell and advertise LLMs for more than what they are, and convince investors to shovel trillions into it. Really Claude should be looking for incentives NOT to do that, and with the American regulator sleeping at the wheel/having its hands greased they probably don't see any reason to change course.

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#299

Post by friendly_chap »

ghostpepper wrote: post #273
roncesvalles wrote: post #254

Earlier quoted context omitted.

You don't even need to pay a 5% hit. Just paste Fable output into Gemini Flash and it will rewrite it in more accessible language.

in my experience, gemini is easily the most grating, condescending, stereotypical LLM voice between opus/fable, codex-5.6, glm-5.2, etc

Me: Paste a go compile error

Gemini: Wow, yeah, haha! That's the final boss of Go compilation errors!

Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA

#300

Post by krige »

uejfiweun wrote: post #285
nxtfari wrote: post #253

If you haven’t been really running and testing these models yourself, they are all benchmaxxed. No matter how close they score to frontier on whatever metric, they always fall apart in real world tasks and their token efficiency is ridiculously bad. Fireworks has incredible incentive to make this claim in a headline, because Fireworks hosting K3 for you is pure profit for them, unlike when they host closed source mod…

All you've said needs the qualifier - "for now!" Look at the trend line. It's clear that if they're not yet at the level of being "good enough" for coding, they will be soon. Sensationalist headlines aside, we all need to be preparing for a world where open models can do pretty much any software tasks you need them to.

https://xkcd.com/605/
Post reply on HN