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

Xiaomi MiMo Reasoning Model

github.com

Post reply on HN
Print view View original

181–190 of 203 posts

Re: Xiaomi MiMo Reasoning Model

#181

Post by loufe »

Arcuru wrote: post #147

From the paper, I was intrigued by how they handled their RL step for Code Data. They trained against hard but solvable code generation tasks by running unit testing. Is that training step done by the other models? > Code Data For coding problems, we curate a high-quality training set comprising open-source datasets and our newly collected problem set. We remove problems without test cases. For problems with golden s…

Is any RL done without unit testing? I would be surprised to hear that that wasn't the case, as it would imply a disregard for accuracy for other model makers, which would be surprising. Perhaps you can do this for small modular problems but not for a problem with a 200k token input?

Re: Xiaomi MiMo Reasoning Model

#182

Post by loufe »

eru wrote: post #176
chvid wrote: post #71

Earlier quoted context omitted.

All LLMs are trained on the same basic blob of data - mostly in English, mostly pirated books and stuff.

That's wrong. Many LLMs are trained on synthetic data produced by other LLMs. (Indirectly, they may be trained on pirated books. Sure. But not directly.)

Likely the case for established model makers, but barring illegal use of outputs from other companies' models, a "first generation" model would still need this as a basis, no?

Re: Xiaomi MiMo Reasoning Model

#183

Post by loufe »

badmonster wrote: post #159

MiMo-7B claims to outperform larger models like Qwen-32B and match OpenAI o1-mini on math/code benchmarks — all with a 7B model trained from scratch. Is this a sign that pretraining + RLHF optimization is finally outpacing scale? Or are we just getting better at benchmarking narrow capabilities?

Qwen 3 or 2.5?

Re: Xiaomi MiMo Reasoning Model

#184

Post by HPsquared »

Leary wrote: post #120
lvl155 wrote: post #65

Why are there so many English-first AI models from China? Are they not interested in serving their own population? Or is it that if they publish Chinese-first models it won't get publicity in the West?

They are not "English-first". Deepseek-R1, for example, reasons in Chinese when you ask it a question in Chinese.

Does that apply in other languages too, like French?

Re: Xiaomi MiMo Reasoning Model

#185

Post by AustinDev »

the_pwner224 wrote: post #162
AustinDev wrote: post #149

Earlier quoted context omitted.

Not just local models but bespoke apps. The number of bespoke apps I've created shot up dramatically in the last 6 months. I use one to do my recipes/meal plan every week. I have one that goes through all my email addresses and summarizes everything daily. I just finished an intelligent planner / scheduler for my irrigation system that takes into account weather forecast and soil moisture levels. If something is anno…

As someone who hasn't used AI for "real" app development (mainly just getting ChatGPT to generate small functions & scripts), do you have any recommendations on what tools or resources I should use to get started with this?

Cursor/Cline/Windsurf are my recommendations for clients. For models stay away from Sonnet 3.7. I find it just lies to you. I'd rather you a slightly less capable model like Sonnet 3.5 where I know it will just make mistakes that won't compile.

I do my planning with a combination of Grok3, and higher power OpenAI models. Once I have plan of what I want to build, I create an implemenation_plan.md with all the steps to build my solution. (Generated by the higher power models) I carefully review this plan and if it looks good, I throw it into agent mode and get to work.

Re: Xiaomi MiMo Reasoning Model

#186

Post by hnfong »

sidibe wrote: post #157
littlestymaar wrote: post #150

Earlier quoted context omitted.

> The most popular one, Baidu, is like garbage compared to Google search It must be very bad when you see the walking turd that Google search has become over the years…

It is. In Chinese speaking countries where there's google available, no one is using Baidu

There's only ONE* Chinese speaking country, at least if you only count those that have a Chinese speaking majority population, or uses Chinese as the official language.

* for various interpretations of one.

Re: Xiaomi MiMo Reasoning Model

#187

Post by lyu07282 »

mring33621 wrote: post #92
apples_oranges wrote: post #12

Earlier quoted context omitted.

exactly, it seems to validate my assumption from some time ago, that we will mostly use local models for everyday tasks.

strong agree my employer talks about spending 10s of millions on AI but, even at this early stage, my experiments indicate that the smaller, locally-run models are just fine for a lot of tech and business tasks this approach has definite privacy advantages and likely has cost advantages, vs pay-per-use LLM over API.

I spend a lot of time working with smaller models, I often had to split the problem into smaller subtasks to make it give acceptable accuracy. With the big models in the cloud you can often get things working much faster, it seems like a tradeoff in engineering time. What was your experience?

Re: Xiaomi MiMo Reasoning Model

#188

Post by erikig »

gizmodo59 wrote: post #94

Its funny to see benchmarks where they omit the top performing models like O3 (Which is the best model in many benchmarks currently) and Gemini Pro/Claude 3.7.

I believe the goal here is to compare them against similar models that are being optimized to run offline or on mobile hardware.

Re: Xiaomi MiMo Reasoning Model

#189

Post by unsupp0rted »

whynotmaybe wrote: post #67
lvl155 wrote: post #65

Why are there so many English-first AI models from China? Are they not interested in serving their own population? Or is it that if they publish Chinese-first models it won't get publicity in the West?

Haven't we reached a situation where English is the de facto language of scientific research, especially AI benchmarks ? It's clearly impossible for me to try anything in Chinese, I'd need a translation.

Less and less, it feels like, every year. I wonder if anybody has hard numbers on that.

Re: Xiaomi MiMo Reasoning Model

#190

Post by tough »

simongray wrote: post #171
tough wrote: post #152

Earlier quoted context omitted.

probably under-indexing of non-english sources by these crawlers. would be interesting if yandex opened some data sets!

And lots of people write on the web using English as a second language, which both reduces the presence of their native language and increases the presence of English.

yep not a native english speaker here and yet my online footprint is mostly english due to software pushing me to learn it
Post reply on HN