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

261–270 of 512 posts

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

#261

Post by SwellJoe »

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

DeepSeek is the fastest model in the benchmarks I've been doing (https://swelljoe.com/post/will-it-mythos/). Followed not so closely by Opus 4.8 and even less closely by Gemini 3.5 Flash and GPT 5.5. I've been really impressed with it, so far. It's also among the best at doing the work, though still trailing the frontier models from Anthropic and OpenAI.

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

#262

Post by IncreasePosts »

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…

A huge class of problems are just toil and drudgery. Maybe ai will give you even more time to dig into juicy problems that are too complex for it to solve, by letting you bypass all the pure toil problems.

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

#263

Post by SwellJoe »

RussianCow wrote: post #104
flexagoon wrote: post #92

Earlier quoted context omitted.

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

Do you mean Flash and not Pro? I haven't tried it personally, but according to OpenRouter, the fastest DeekSeep V4 Pro providers are only ~50tps. That's slower than Claude Opus. https://openrouter.ai/deepseek/deepseek-v4-pro?sort=throughp...

In recent benchmarking I've been doing, DeepSeek V4 Pro was the fastest of 21 models, by a comfortable margin (https://swelljoe.com/html/bench-report-final.html). Faster than Claude Opus 4.8, which was the second fastest (Mistral doesn't count because it seems to have refused to participate). But, it's a limited data set, just a few benchmark runs of a limited set of tasks. It's entirely possible I happened to be calling the API at its least busy time and maybe Claude got hit during a busy time.

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

#264

Post by SwellJoe »

tmaly wrote: post #120
miroljub wrote: post #61

Earlier quoted context omitted.

MiMo and DeepSeek are not cheap. Anthropic and OpenAI are expensive for what they provide.

Energy is likely more abundant in China. I am not sure about compute, but that must be part of reason for such drastic price differences.

They're leaving us in the dust on solar, while our current administration is still trying to put people in the ground to dig up more coal and die of black lung. https://en.wikipedia.org/wiki/Solar_power_in_China

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

#265

Post by Muromec »

fartfeatures wrote: post #93
pianopatrick wrote: post #81

Earlier quoted context omitted.

We fit in for the things that are not artificial. So long as AI lives in server farms, humans will be needed for tasks in the physical world. It's only if we combine AI with robots that things get really dicey.

This is very dystopian in my opinion. I'm not the arms, legs, sensors and actuators for a machine super intelligence. I wouldn't treat another human as my slave because they aren't as intelligent as I am any more than I would expect to become a slave for a machine. This is our world (for now) and that is why we fit in. Not because we can serve.

You don't need ai superintelligence, just plain capitalism is enough

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

#266

Post by esperent »

AgentMasterRace wrote: post #209
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.

All the models have broken estimates. They're trained heavily on jira and GitHub tasks and issues, that's why their estimates are human.

Even for humans the estimates are way off, unless it's based on data that has some serious padding.

That said, it'll often say "2 days of work" and then complete the coding in 30 minutes, and while that's amusing, afterwards, I'll need to manually test, or send to other people for review, or realize the agent only actually did half the work and I need to do a second pass (or a third etc.) and then often getting the feature in does genuinely take two days.

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

#267

Post by anothereng »

philipkglass wrote: post #60
harel wrote: post #36

A few things in life I can't fully grasp why they are so sought after. One is that constant need to exhibit growth. As if being massive and staying as massive is not good enough, one has to always and continuously grow. The other is constant speed increases. We're already operating at 50x speed. My output is much wider and so much faster, I am sometimes my own bottleneck. And now as if that is not enough we want more…

I remember when I had to wait minutes to get a high resolution image over a dialup connection. When computer and communications hardware advanced enough that I could get 30 high resolution images every second, there were brand new uses. In the case of LLMs, I could imagine that much faster operations allow you to introduce them as parts of systems that need to react to the real world at high speed, like factory equip…

yeah at a very high speed the agent can code the solution when you ask it for something on the go. Imagine it be able to make a feature as fast as a website loads sometime in the future that would feel like magic

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

#268

Post by guilamu »

miroljub wrote: post #256
chrismustcode wrote: post #86

Earlier quoted context omitted.

You don't consider Input $0.435 Output $0.87 cache read $0.003625 per million tokens for near frontier intelligence cheap?

No. They still have enormous profit margins on inference with these prices.

Any source to backup this claim, pretty please?

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

#269

Post by coderbants »

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…

It cuts both ways. Sometimes I ask Gemini 3.5 Flash to do something for me and it kicks it out almost instantly and it works great, and it's a bit scary how quickly it can do that.

Then I ask it to do something else and it goes off-road and where I used to be able to interject with a "wow wow wow, that's not right", by the time I see the text on screen and react it's already made massive changes. Short of making it commit between every edit it's hard to prevent it from going wrong as quickly as it goes right (and even then, it can make a boo-boo on a remote API too depending on how much privilege it has).

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

#270

Post by drob518 »

yunohn wrote: post #240
goyozi wrote: post #130

Earlier quoted context omitted.

I’m rewriting our integration test suite to run tests in parallel. I have the changes split across 7 branches, and each needs to be fixed to have no flaky tests. I told it I want 3 consecutive CI runs with no flakes and no artificial fixes / assert removals etc. We’ll see what comes out; it’s almost a side project so there’s not much to lose other than some of my weekly limit that resets soon.

> a side project so there’s not much to lose other than some of my weekly limit that resets soon Basically the entire token-maxxing AI hype train in a nutshell. Lovely!

I’m curious when folks will tire of lighting money on fire. Companies are already starting to scale back a bit, but the AI companies are still nowhere near profitability.
Post reply on HN