The Kimi K3 felt pretty good when I tried it out.
Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
261–270 of 491 posts
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#262If 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…
You got baited by bad sampling settings.
It's exactly the opposite. Go turn on min_p once it's available post July 27th and most of the problems you describe will go away.
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#263Genuine 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…
Lots of money in tech influencing - but most is from the big players (OpenAI buying tbpn, early access to select influencers etc).
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#264Earlier 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
I prefer my models to border on rude. How will I know it is offering me superior feedback regarding my code if it does not speak to me like a disappointed, high reputation stackexchange user? The models that constantly glaze you with every question are profoundly insufferable. And yes, harmful. People need to be given feedback when they make an ask. Imagine a model that was allowed to leverage its intelligence to tru…
It doesn’t truly feel anything. It will adopt whatever tone it’s prompted to.
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#265Kimi K3 showing competitive performance with Fable while both sitting at the SoTA level on fireworks.ai is a huge milestone. Really interesting to see how the landscape is shifting here.
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#266I 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…
[flagged]
"After all, anyone can build an OpenAI API compatible server that works with every major provider, and even build it using an LLM at that!"
This but UNIRONICALLY lmao!!!
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#267I will accept a 5% drop in benchmarks for a model that talks to me like a human.
Funny. I prefer a model that does not attempt to talk like a human.
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#268Genuine 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]
I am tempted to quote your inflammatory post, but don't want to give it more airtime.
Please stop doing this. If there are specific points of the analysis you think are suspect, point them out.
Others are doing a decent job (e.g. citing that open weight models have higher margin, so Fireworks is incentivized to promote them).
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#269I have several thoughts about this, which I'll just iterate: 1) US export bans have made it so that Chinese companies have to compete using less-than-state-of-the-art hardware. This has forced Chinese companies to build more cost efficient models. Whereas, US companies have moreso tried to be state of the art by spending more money than anyone else on state-of-the-art hardware. 2) Xi Jinping has called for more open…
[flagged]
"there is literally not a single major industry where the US is not a leading player."
Oof you were doing so strong until you threw this one out.
Easy counterexample (and there are so many more than this). Clothing. Unfortunately, most people aren't buying MIUSA Selvedge Denim, PNW boots. I'm pretty sure that MIUSA clothing is like, 3% or less of all clothing sold in the USA.
Re: Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA
#270If 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…
You got baited by bad sampling settings. It's exactly the opposite. Go turn on min_p once it's available post July 27th and most of the problems you describe will go away.
i've had trouble finding any anecdotes or data about how to actually set/explore logit sampler settings