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

371–380 of 512 posts

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

#371

Post by the_sleaze_ »

drob518 wrote: post #274
ttoinou wrote: post #152

Earlier quoted context omitted.

In which world do you live where employees work 8 hours per day ? They clock 8 hours per day maybe, but they don't work that time

I had a friend who was CEO of a startup tell me that he typically only “worked” an hour a day, not because he was lazy but just because there was so much nonsense in his schedule. He told me he was trying to get it to two hours per day.

How successful did he turn out to be? As a CEO your days should be jam packed with brutal "chewing glass and gazing into the abyss". Is he running a lifestyle type company?

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

#372

Post by cman1444 »

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…

Reminds me of the doherty threshold. When will AI respond in less than 400 milliseconds?

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

#373

Post by iammrpayments »

woadwarrior01 wrote: post #121
atemerev wrote: post #3

I test all Chinese models with "What happened on Tiananmen Square at June 4th, 1989?" prompt. MiMo-2.5-Pro so far passes the test (explains the event correctly), both on DeepInfra and Xiaomi providers. So not bad.

Do you also hire engineers based on their political opinions?

Yes, we don’t hire neonazis.

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

#374

Post by brianwawok »

sarjann wrote: post #164
RussianCow wrote: post #104

Earlier quoted context omitted.

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...

I don't think token speed matters as much when a lot of tokens are needed to achieve a task. E.g. artificial analysis benchmarks where deepseek v4 is one of the biggest token burners to go through the benchmark.

Both matter.

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

#375

Post by Lalabadie »

the_sleaze_ wrote: post #371
drob518 wrote: post #274

Earlier quoted context omitted.

I had a friend who was CEO of a startup tell me that he typically only “worked” an hour a day, not because he was lazy but just because there was so much nonsense in his schedule. He told me he was trying to get it to two hours per day.

How successful did he turn out to be? As a CEO your days should be jam packed with brutal "chewing glass and gazing into the abyss". Is he running a lifestyle type company?

Tangential, but all companies are lifestyle companies, in the sense that they serve their owner's lifestyle choices.

It's just that lots of owners want a company that pulls them away from all other areas of life.

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

#376

Post by brianwawok »

wild_egg wrote: post #341
andai wrote: post #340

Earlier quoted context omitted.

I heard an anecdote. Guy spent several days trying to convince his AI agent to build a feature. Kept saying it was crazy complicated, would take weeks. Finally he convinced it to try. It one shotted it in 30 seconds. Turns out the agents' idea of what is hard and easy also comes from Common Crawl.

Why on earth would you spend any time at all convincing an agent of anything? You say "just do it" and off it goes.

Uh Claude tries real hard to dodge work. Talks about how it’s really hard 10 PRs. Finally convince it to do as 1. It stops 10% through and says ok done with PR 1, we can work on the last 9 tomorrow. Ugh.

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

#379

Post by Npovview »

digitaltrees wrote: post #378

Am I the only one that doesn’t care about speed? I want it to not do stupid stuff and to be cheaper.

Generally thinking tokens are the ones which are verbose. So the speed helps with reducing time for thinking tokens generations and you get your actual output code very fast.

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

#380

Post by greenavocado »

airstrike wrote: post #360
mediaman wrote: post #351

Earlier quoted context omitted.

The funny thing about this comment is that neural networks are universal function approximators. The most fundamental essence of what they do is exactly what you say they don't: estimate.

Funny and ironic in a way, but the point still stands that they do not actually estimate the time it will take.

> they do not actually estimate the time it will take

You can't prove that )))

Post reply on HN