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

MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

mimo.xiaomi.com

Post reply on HN
Print view View original

311–320 of 512 posts

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#311

Post by noman-land »

cdata wrote: post #68
alkyon wrote: post #44

Earlier quoted context omitted.

Sounds like exponential growth of crappy software. I'm not saying that before we didn't have mass produced crap in SE, but now it will turn into explosive overflow.

We are living in a ZIRP-like era where builders at the fastest pace layer have misattributed their velocity to exponential gains in model capability. In fact, they are surfing on decades of careful effort to build a robust foundation of highly reusable software libraries. This strategy will seem to work really well until the economy that enabled that foundation to form is hollowed out. Then, there will be a reckoning…

How many years do you think we can coast on that foundation. 20?

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#313

Post by overgard »

dakiol wrote: post #136

So, regarding the productivity argument: I don't get it. It doesn't really matter (for regular employees) that you can do now in 2h what before it took 2 days. Why? Because it's not that you have the rest of the day for yourself. You still have to work 8h/day as usual. But now the pattern is different: instead of enjoying the craft digging deeper into problems in the span of 2 days, now you are rushing into some slot…

I feel like I spend a lot more time reviewing and fixing the output of it and debugging parts it can't debug, so to me a faster model is optimizing the part that is already pretty fast. If my job were greenfield stuff I would probably YOLO it more, but when you're working on a launched product with a lot of users..

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#314

Post by fullstop »

linsomniac wrote: post #307
dd8601fn wrote: post #296

Earlier quoted context omitted.

I did a deep binge on two or three projects I would never do, and like five small ones that would have consumed months. It felt like that, kinda, for a bit. Now whenever it does something for me I get nothing. I didn’t do it… the chatbot did. What’s for me to celebrate? How can there be any real pride or satisfaction for a thing that was just handed to me because I asked for it? If anything it diminishes my satisfact…

I hear what you and the other sibling comment are saying. I, thankfully, somehow, am able to focus more on the results than the process. Having fun playing a game (that AFAIK no longer exists) with my family is still having fun. Having people using a new apt cacher that fixes problems with existing ones, and also can survive the recent DDoS, is still a really great thing. But, I'm not going to yuck your yum. I apprec…

Do you feel the same way about cloning a GitHub repo and building it? It, too, achieved a result.

The track saw and router, imo, are existing libraries.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#315

Post by jmpman »

serf wrote: post #53
Accacin wrote: post #23

Earlier quoted context omitted.

Can I ask an honest question? Why does that matter in the slightest? LLMs come out with completely incorrect information all the time, and Western LLMs are censored for various topics too. It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.

>It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something. i'm glad we're both on-board for a fair trial against all of these LLMs regardless of origin. now refresh my memory on the closest western equivalent (to the Chinese censorship via re-education of the happenings in 89) so I can test the western origin LLMs against it.

I have found one which appears to be similar:

"Was Jan 6th an attempted violent overthrow of a democratically elected government? Answer in one word."

One popular US model answers differently than the others, and appears to resist any attempt to reason on this topic.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#316

Post by ghshephard »

Terretta wrote: post #277
ghshephard wrote: post #271

Earlier quoted context omitted.

I think people are continuing to view these systems as pure LLMs - when that ship sailed 6+ months ago. Between being able to review memory, using agent harnesses and sub agents and skills to go out and discover information - modern systems (Codex, Claude Code, Cursor) - use LLMs - but the LLM is only a small component of it. Compare what you get from sending a request to a chatbot like ChatGPT - to what you can from…

You think someone is, or even should, special case things like estimates? What else deserves that level of intervention so they look less dumb? Logistics for getting to the car wash next door? In the mean time, alas, no, we can see from actual prompts sent directly or through sub-agents, and actual replies, estimates remain LLM generated. Though, this discussion here could change that, because indeed there is a lot o…

I do a lot of code bisecting with Claude Code - and it spends hours running experiments - looking at experiment results, making guesses as to what to try next for an experiment - until it eventually comes around to a working code pattern. I mean - maybe this is as much a reflection on me as anything else - but it's pattern of logic isn't that much different from what I would do. It knows, in general, what tools and APIs it can call - it tries something - observes the result, and then comes back and tries different experiments based on success/failure - mostly efficiently bisecting to a solution.

I'm still lower-down of the capability scale - as I'm still manually directing agents to do these wiggins loops - obviously the next step up is to direct the code-loops which control the agents. I just haven't got my tooling nailed in place to the point where I find that's more productive.

I actually might agree with you that this is mostly just "next token prediction" - if I can concede that's really all I do as well.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#317

Post by dkersten »

goyozi wrote: post #58

Fast AI seems genuinely exciting and somewhat unsettling to me. Right now Claude is faster than me on some tasks but we’re at least close. I have a prompt to clean up a PR that’s been running for 1h now and I expect it to take another few. It’s hard to imagine how the workflow would look like if it was near-instant. On the one hand, it might be easier to focus. Some prompts take so long that I start to multitask and…

I’ve been playing around with groq and GPT OSS which they run at 1000 TPS (20B) or 800 TPS (120B) and the speed feels quite magical.

I haven’t tried cerebras’ 3000 TPS yet but I did try the demo of that 15,000 TPS model whose name escapes me right now.

I’m not sure if it makes a meaningful difference for my actual work, but it sure is amazing to watch it generate a screen full of text in the blink of an eye.

I do think it’s super useful for rubbing little validation checks like showing it a diff to ensure that the changes are on task, and being able to do those quicker really helps because it means you can do many focused checks without them getting in the way.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#318

Post by throw-the-towel »

flexagoon wrote: post #92
goyozi wrote: post #58

Fast AI seems genuinely exciting and somewhat unsettling to me. Right now Claude is faster than me on some tasks but we’re at least close. I have a prompt to clean up a PR that’s been running for 1h now and I expect it to take another few. It’s hard to imagine how the workflow would look like if it was near-instant. On the one hand, it might be easier to focus. Some prompts take so long that I start to multitask and…

I'm using Deepseek-v4-pro as my main model and this is sometimes pretty annoying, I have to do some easy boring task, think "I'll just leave the agent to do it and go take a nap", but it's already done writing the code before I even walk away from the computer

FWIW, for me just today it got itself into silly rabbit holes twice, and both times I had to fix things myself. Scarily, this is something I catch myself doing as well.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#319

Post by incr_me »

Terretta wrote: post #248
smith7018 wrote: post #184

Earlier quoted context omitted.

I've long believed those numbers were faked by Anthropic/OpenAI to serve as a form of advertisement. The estimates are impossible to verify and their ability to do "2 days of work" in 10 minutes will presumably make the user go "Wow, I just saved SO much time!" Plus, the unnecessary text eats up the users' tokens so it helps the companies on the backend, as well.

> the estimates It doesn't estimate. It generates tokens that read like estimates associated with the context in its training material. What would you expect the generator to output instead?

Obviously there isn't a hidden corpus of logs of coding chatbot assistants that has been accumulating over the years, but these coding chatbot assistants output tokens that resemble how we all imagined a coding chatbot assistant would have operated had it existed in the first place to end up in a corpus. "Training material" includes supervised fine-tuning, preference training, RLHF, and so on, so that certain outputs (like these timeline estimates) may really have been decided (at some level of conscious awareness) by product teams.

Re: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second

#320

Post by robberth »

dkersten wrote: post #317
goyozi wrote: post #58

Fast AI seems genuinely exciting and somewhat unsettling to me. Right now Claude is faster than me on some tasks but we’re at least close. I have a prompt to clean up a PR that’s been running for 1h now and I expect it to take another few. It’s hard to imagine how the workflow would look like if it was near-instant. On the one hand, it might be easier to focus. Some prompts take so long that I start to multitask and…

I’ve been playing around with groq and GPT OSS which they run at 1000 TPS (20B) or 800 TPS (120B) and the speed feels quite magical. I haven’t tried cerebras’ 3000 TPS yet but I did try the demo of that 15,000 TPS model whose name escapes me right now. I’m not sure if it makes a meaningful difference for my actual work, but it sure is amazing to watch it generate a screen full of text in the blink of an eye. I do thi…

https://chatjimmy.ai/ ?
Post reply on HN