Hacker Newsnew | past | comments | ask | show | jobs | submit | mirrir's commentslogin

In the same sense its that the descriptive machinery isn't fully developed. If we wrote all of our proofs in a Godelian representation of statements we would also come out with tomes per proof.

> Baidu and Xiaomi don't create models. That's handled by other entities in the China market.

12 days ago: https://huggingface.co/baidu/ERNIE-5.5-Flash-Base 20 days ago: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL


You didn't read further..

>Maybe create a model of their own to see if they can improve the business case in one dimension or another.

All done in the context of experimentation to improve economics not intelligence.

Baidu and Xiaomi are trying to figure out how to make money. Not how to make models. Making models is not their business and they don't want to be in that business. China is full of dime a dozen PhDs who can make models. They don't want to do that, they want to make money. That's the point.

They want to understand what are the conditions required for model providers to offer them a model, any model, that performs in an economic sense at scale. That may require creating a model or two as experiments, but that is not at all an indication that they want to change their business to model creation. Nor even get into the business of model creation.

Model creation is just not a good business for the likes of Xiaomi, Samsung, Apple et al. If they have to, fine. But it's clear from their statements that they really don't want to because it's, currently, a terrible business.


No I did read further. I just don't think your perspective is correct. Baidu has doubled its cloud revenue YoY and so has Xiaomi's AI division. They are making money. They are worried that they will not be able to sustainably maintain that growth.

> Baidu and Xiaomi experiment with models. Test the efficacy of different models. Get an idea of the relative economics of different models. Maybe create a model of their own to see if they can improve the business case in one dimension or another. > Baidu and Xiaomi are trying to figure out how to make money. Not how to make models. Making models is not their business and they don't want to be in that business. China is full of dime a dozen PhDs who can make models. They don't want to do that, they want to make money. That's the point.

Both are currently in the business of providing efficient compute and deployment platforms as well as first party models. From Baidou's perspective their biggest competition in the space is squarely Alibaba who has attributed a significant amount of their massive 45% growth this quarter to Qwen and their compute platform in general.[1] Making money and making models are not opposed, but the structure of the business matters significantly.

> What they're saying is that, in their role as customers for these models, they're a bit confused about the business case. I think that's a fair statement. They've presumably put a lot into finding out how to make money out of these models, and presently, the returns are not there with respect to the bottom line. Additionally, their experiments have given them enough background to feel comfortable asking, openly, where exactly everyone else feels the returns will come from?

I don't think I'd characterize their positions as this. The returns are there. Their quarterly financials explicitly say so. From the statements in the article, they are concerned with the continuation of their downstream customers' spending. In Baidu's case it hasn't been enough to offset their advertising losses. As providers they need better downstream products and actual value adds, otherwise they will not be able to continue providing the quarterly guidance of growth that they have been communicating to their investors.

> But it's clear from their statements that they really don't want to because it's, currently, a terrible business.

It is not.

[1]: https://www.alibabagroup.com/en-US/document-2027233133950140...


yes but that's your own project. its odd to not disclose that while calling other's work archaic.

Its a hollow shell RC car with air canisters.


Tesla making a hollow shell full of hot air would seem appropriate somehow.


The page talks about a bunch of weight reduction tech, but I didn't see an actual final weight for the Rocket model? Given that it can support itself with "downforce" (and no thrusters, and apparently not much momentum?) at the top of the loop it's got to be pretty light...


(Ah, the youtube "designer interview" says around 1700kg (the first-gen was 1300kg; formula one has a minimum weight of 800kg.)



I'm not an ornithologist but birds don't need to consume jet fuel to fly hundreds of miles either.


But of course it helps.


True, after ingesting a stomach's worth of jet fuel the bird is powered for the rest of its life.


In bird culture, this is considered a dick move


Not really, it’s mainly a defense mechanism against hunters


from what i understand this is CrossPoint.


CrossInk is a fork of CrossPoint but Julia is a major maintainer of CrossPoint. FreeInk's SDK powers both


Oh yeah, indeed. Which is the rebrand haha


replace "successful product" with "useful artifact" and you'll get more of the common ground with less of the pedantics.


My university had a great policy for this. For every major assignment you went through interview grading. if you failed it you lost 60% of that grade.


> interview grading

Would you mind expanding on what exactly that entails?


Yes absolutely. For large code writing assignments and projects grad students would be tasked with writing the code. After submission they had to schedule a 15-20 minute chat with a grad student in the course for Interview Grading. Through that process the grad would ask why the student made specific choices in their code, where improvements could have been made, and the process they took to solve the task. It wound up being a pretty effective and kind way to get people to not really care as much about referencing things like StackOverflow (no GPT at the time), and helped make a lot of students need to care much more aabout the why of their code.


There is voodoo in begging the question though.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: