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

Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

moonshotai.github.io

Post reply on HN
Print view View original

131–140 of 442 posts

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#131

Post by rcxdude »

NiloCK wrote: post #129

Maybe a dumb question but: what is a "reasoning model"? I think I get that "reasoning" in this context refers to dynamically budgeting scratchpad tokens that aren't intended as the main response body. But can't any model do that, and it's just part of the system prompt, or more generally, the conversation scaffold that is being written to. Or does a "reasoning model" specifically refer to models whose "post training"…

The latter. A reasoning model has been finetuned to use the scratchpad for intermediate results (which works better than just prompting a model to do the same).

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#133

Post by burroisolator »

isusmelj wrote: post #122

Is the price here correct? https://openrouter.ai/moonshotai/kimi-k2-thinking Would be $0,60 for input and $2,50 for 1 million output tokens. If the model is really that good it's 4x cheaper than comparable models. It's hosted at a loss or the others have a huge margin? I might miss something here. Would love some expert opinion :) FYI: the non thinking variant has the same price.

In short, the others have a huge margin if you ignore training costs. See https://martinalderson.com/posts/are-openai-and-anthropic-re... for details.

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#134

Post by cantor_S_drug »

refulgentis wrote: post #97
cantor_S_drug wrote: post #73

Earlier quoted context omitted.

In CS algorithms, we have space vs time tradeoffs. In LLMs, we will have bigger weights vs test-time compute tradeoffs. A smaller model can get "there" but it will take longer.

I have spent the last 2.5 years living like a monk to maintain an app across all paid LLM providers and llama.cpp. I wish this was true. It isn't. "In algorithms, we have space vs time tradeoffs, therefore a small LLM can get there with more time" is the same sort of "not even wrong" we all smile about us HNers doing when we try applying SWE-thought to subjects that aren't CS. What you're suggesting amounts to "monke…

If "not even wrong" is more wrong than wrong, then is 'not even right" more right than right.

To answer you directly, a smaller SOTA reasoning model with a table of facts can rederive relationships given more time than a bigger model which encoded those relationships implicitly.

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#135

Post by throwaway314155 »

0xjmp wrote: post #130
barrell wrote: post #114

Earlier quoted context omitted.

I believe they mean distribution (inference). The Chinese model is currently B.Y.O.GPU. The American model is GPUaaS

Why is inference less attainable when it technically requires less GPU processing to run? Kimi has a chat app on their page using K2 so they must have figured out inference to some extent.

tl;dr the person you originally responded too is wrong.

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#136

Post by JJax7 »

an0malous wrote: post #123
JJax7 wrote: post #28

Earlier quoted context omitted.

Love seeing this benchmark become more iconic with each new model release. Still in disbelief at the GPT-5 variants' performance in comparison but its cool to see the new open source models get more ambitious with their attempts.

Why is this a benchmark though? It doesn’t correlate with intelligence

I'm not saying its objective or quantitative, but I do think its an interesting task because it would be challenging for most humans to come up with a good design of a pelican riding a bicycle.

also: NITPICKER ALERT

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#137

Post by DrNosferatu »

the_mitsuhiko wrote: post #51
seunosewa wrote: post #46

Earlier quoted context omitted.

The Chinese are doing it because they don't have access to enough of the latest GPUs to run their own models. Americans aren't doing this because they need to recoup the cost of their massive GPU investments.

And Europeans don't it because quite frankly, we're not really doing anything particularly impressive with AI sadly.

Europe should act and make its own, literal, Moonshot:

https://ifiwaspolitical.substack.com/p/euroai-europes-path-t...

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#138

Post by ok_dad »

HighGoldstein wrote: post #127
an0malous wrote: post #123

Earlier quoted context omitted.

Why is this a benchmark though? It doesn’t correlate with intelligence

What test would be better correlated with intelligence and why?

When the machines become depressed and anxious we'll know they've achieved true intelligence. This is only partly a joke.

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#139

Post by NiloCK »

rcxdude wrote: post #131
NiloCK wrote: post #129

Maybe a dumb question but: what is a "reasoning model"? I think I get that "reasoning" in this context refers to dynamically budgeting scratchpad tokens that aren't intended as the main response body. But can't any model do that, and it's just part of the system prompt, or more generally, the conversation scaffold that is being written to. Or does a "reasoning model" specifically refer to models whose "post training"…

The latter. A reasoning model has been finetuned to use the scratchpad for intermediate results (which works better than just prompting a model to do the same).

I'd expect the same (fine tuning to be better than mere prompting) for most anything.

So a model is or is not "a reasoning model" according to the extent of a fine tune.

Are there specific benchmarks that compare models vs themselves with and without scratchpads? High with:without ratios being reasonier models?

Curious also how much a generalist model's one-shot responses degrade with reasoning post-training.

Re: Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

#140

Post by beepbooptheory »

an0malous wrote: post #123
JJax7 wrote: post #28

Earlier quoted context omitted.

Love seeing this benchmark become more iconic with each new model release. Still in disbelief at the GPT-5 variants' performance in comparison but its cool to see the new open source models get more ambitious with their attempts.

Why is this a benchmark though? It doesn’t correlate with intelligence

I think its cool and useful precisely because its not trying to correlate intelligence. It's a weird kind of niche thing that at least intuitively feels useful for judging llms in particular.

I'd much prefer a test which measures my cholesterol than one that would tell me whether I am an elf or not!

Post reply on HN