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

241–250 of 491 posts

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

#241

Post by equinumerous »

apatheticonion wrote: post #37

I love the Chinese models. I use DeepSeek exclusively and now Kimi K3 offers a great planning assistant for more advanced coding tasks. DeepSeek v4 Flash is extremely fast and is able to handle pretty much anything I've thrown at it (I use mostly Rust, PSQL, Angular and Terraform). I self host Bifrost as my LLM gateway, though I wish LLM vendors would do monthly/daily automatic billing (like VPS providers do) rather…

As someone who is also eyeing Bifrost, I am curious to know what made you choose Bifrost at all / why you decided to use an LLM gateway. I also was considering OpenRouter, since it provides pretty much every model, with same-day releases for new models. One thing that is attractive to me about Bifrost is that if I decide to leave OpenRouter tomorrow, I can do so without touching any other part of my stack; I'm hoping self-hosting models becomes more viable, and then I can become less dependent on third party LLM providers like OpenAI/Anthropic/OpenRouter, and I would not need to worry about a model that I depend on suddenly being deprecated.

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

#242

Post by apatheticonion »

adamisnotroman wrote: post #230
apatheticonion wrote: post #37

I love the Chinese models. I use DeepSeek exclusively and now Kimi K3 offers a great planning assistant for more advanced coding tasks. DeepSeek v4 Flash is extremely fast and is able to handle pretty much anything I've thrown at it (I use mostly Rust, PSQL, Angular and Terraform). I self host Bifrost as my LLM gateway, though I wish LLM vendors would do monthly/daily automatic billing (like VPS providers do) rather…

I didn't realize that OpenRouter had a mark up. Is it a flat mark up across the board or depending on the model?

Under $20 it's a flat $0.8 fee. Over $20 it's +5.5%

+ credit card charges (+1.5%)

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

#243

Post by brunooliv »

Genuine question: can these posts be paid to hype the open source models? If yes, what would be the purpose?

On my work tasks, FastAPI Python and Springboot Java on a modern SaaS product, the only open model that can do tasks well and efficiently is Qwen3.7-Max.

In all my experiments, both GLM-5.2 and Kimi are busy grepping around the codebase for ALMOST 70-80K tokens before writing anything and when they do it typically breaks the code… it feels to me that these models are good but only when you write out a super detailed spec of the task just like it was done a year ago… Qwen3.7 just… does it

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

#244

Post by singingtoday »

onlyrealcuzzo wrote: post #187
bjourne wrote: post #179

I'm skeptical. According to arena.ai, Fable 5 dominates almost every category : https://arena.ai/leaderboard Kimi K3 has an edge in WebDev but struggles to reach top 10 in many other categories.

In my experience, Fable is not even close to Sol 5.6 High (not even the max tier) for coding. 1) it's substantially slower. 2) it's substantially more expensive. 3) it's code is considerably worse. It's a joke when you consider what you get for what you pay for.

This is very interesting to me because I find sol to be inferior at code generation, but superior at conversation and code review.

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

#245

Post by malshe »

the_sleaze_ wrote: post #211
rogerrogerr wrote: post #31

Earlier quoted context omitted.

The apparent bias may be explainable as it’s not remarkable for OpenAI or Anthropic to be slightly ahead. It _is_ remarkable for an open weights model to be better than the closed models from the trillion dollar (allegedly) companies.

I believe the Chinese government is angling to destroy the western economy and rise from the ashes. Instead of a billion a day to bomb some buildings and bridges they're intentionally hamstringing the biggest concentration of speculation in history

I agree. The commenter you replied to makes it sound like the Chinese models are coming out of tiny startups with meager resources. It's really not a David vs Goliath story.

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

#246

Post by abdullahkhalids »

semilin wrote: post #215
abdullahkhalids wrote: post #212

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

Why? LLMs are not humans.

Doors aren't humans either, yet we design their handles and locks to be graspable and manipulable by humans.

The purpose of technology is to serve humans. Therefore, technology must conform as much as possible to human sensibilities rather than vice versa.

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

#249

Post by roncesvalles »

brunooliv wrote: post #243

Genuine question: can these posts be paid to hype the open source models? If yes, what would be the purpose? On my work tasks, FastAPI Python and Springboot Java on a modern SaaS product, the only open model that can do tasks well and efficiently is Qwen3.7-Max. In all my experiments, both GLM-5.2 and Kimi are busy grepping around the codebase for ALMOST 70-80K tokens before writing anything and when they do it typic…

[flagged]

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

#250

Post by 4b11b4 »

perching_aix wrote: post #225
4b11b4 wrote: post #218

Earlier quoted context omitted.

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

Maybe we're prompting it different, but it's not "trying to be my friend" for sure, nor am I trying to be "its" friend either. Or at least I'm sufficiently oblivious to its advances, and find it unthinkable to form such a bond :) On the flipside, it does spuriously make hilarious remarks like "Good data.", which I find pretty funny specifically because it comes across as just silly. Not sure how it'd be harmful eithe…

In general I'm referring to the contrast between Claude and GPT...

where Claude might follow some tangent idea you mentioned and tell you how its interesting and give you some elaborate response about that little one remark you made

whereas GPT/Codex would take that small comment and probably look up some code to see if what you're talking about is even related to the task at hand

Post reply on HN