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

Magistral — the first reasoning model by Mistral AI

mistral.ai

Post reply on HN
Print view View original

401–410 of 444 posts

Re: Magistral — the first reasoning model by Mistral AI

#401

Post by glomgril »

SoMomentary wrote: post #368
orbital-decay wrote: post #293

Earlier quoted context omitted.

This terrible and vague stereotyping about "China" while having no clue about the subject should have no place on HN but somehow always creeps in and is upvoted by someone. DeepSeek is not "China", they had nobody to copy from, they released their first 7B reasoning model back in April 2024, it was ahead of then-SotA models in math and validated their approach. They did a ton of new things besides training a reasonin…

I thought it had been bandied about that Deepseek had exfiltrated a bunch of data from OpenAI's models, which was then used to train theirs? Did this ultimately prove untrue? My apologies, I don't always keep up on the latest drama in the AI circles - so maybe that has been well proven wrong.

one man's exfiltration is another man's distillation `¯\_(ツ)_/¯`

you could say they're playing by a different set of rules, but distilling from the best available model is the current meta across the industry. only they know what fraction of their post-training data is generated from openai models, but personally i'd bet my ass it's greater than zero because they are clearly competent and in their position it would have been dumb to not do this.

however you want to frame it, they have pushed the field forward -- especially in the realm of open-weight models.

Re: Magistral — the first reasoning model by Mistral AI

#402

Post by notnullorvoid »

dwedge wrote: post #216

Their OCR model was really well hyped and coincidentally came out at the time I had a batch of 600 page pdfs to OCR. They were all monospace text just for some reason the OCR was missing. I tried it, 80% of the "text" was recognised as images and output as whitespace so most of it was empty. It was much much worse than tesseract. A month later I got the bill for that crap and deleted my account. Maybe this is better…

I wouldn't trust any of these LLM teams to produce a good OCR model. OCR from 10 years ago is better than the crap they put out.

Re: Magistral — the first reasoning model by Mistral AI

#403

Post by LordDragonfang »

otabdeveloper4 wrote: post #319
robmccoll wrote: post #267

Earlier quoted context omitted.

What are we doing when we think?

We don't know yet. But we do know it's certainly not statistical token prediction. (People can do statistical token prediction too, but that's called "bullshitting", not "thinking". Thinking is a much wider class of activity.)

Do we know that with certainty? Do we actually?

Because my understanding is that how "thinking" works is actually still a total mystery. How is it we no for certain that the basis for the analog electric-potential-based computing done by neurons is not based on statistical prediction?

Do we have actual evidence of that, or are you just doing "statistical token prediction" yourself?

Re: Magistral — the first reasoning model by Mistral AI

#404

Post by cluckindan »

LordDragonfang wrote: post #400
andrepd wrote: post #364

Earlier quoted context omitted.

It's a misleading "term of art" which is more accurately described as a "term of marketing". Reasoning is precisely what LLMs don't do and it's precisely why they are unsuited to many tasks they are peddled for.

How are you defining "reasoning" such that you are confident that LLMs are definitely not doing it? What evidence do you have to that effect? (And are you certain that none of your reasoning applies to humans as well?)

They don’t ”think”.

https://arxiv.org/abs/2503.09211

They don’t ”reason”.

https://ml-site.cdn-apple.com/papers/the-illusion-of-thinkin...

They don’t even always output their internal state accurately.

https://arxiv.org/abs/2505.05410

Re: Magistral — the first reasoning model by Mistral AI

#405

Post by megalomanu »

kamranjon wrote: post #398
megalomanu wrote: post #342

We just tested magistral-medium as a replacement for o4-mini in a user-facing feature that relies on JSON generation, where speed is critical. Depending on the complexity of the JSON, o4-mini runs ranged from 50 to 70 seconds. In our initial tests, Mistral returned results in 34–37 seconds. The output quality was slightly lower but still remain acceptable for us. We’ll continue testing, but the early results are prom…

I am curious why you would choose a reasoning model for JSON generation? I was recently working on a user facing feature using self-hosted Gemma 27b with VLLM and was getting fully formed JSON results in ~7 seconds (even that I would like to optimize further) - obviously the size of the JSON is important but I’d never use a reasoning model for this because they’re constantly circling and just wasting compute. I haven…

It is for generating a big nested JSON, quite complex from a business standpoint (lots of different business concepts). We didn't have good results with simple models.

Re: Magistral — the first reasoning model by Mistral AI

#406

Post by Xmd5a »

kgwgk wrote: post #359
psychoslave wrote: post #335

Earlier quoted context omitted.

What do you mean with work more than 10h/day for intellectual work? You don't stop to think the moment you are away from the production machine. And the exact opposite can often happen: you go away from the computer/board/paper/office, make a walk trying to wander at something else as far as you can stear consciousness, and then the solutions/ideas land in your mind.

You’re not wrong but what did the commenter above meant with “50 hours+/week”? Weeks have three times as many hours. Years also have many more than 218 days. Anyway I found an official survey saying that 40% of them work more than 50 hours per week (but fewer weeks than regular employees) so I guess it’s not so rare (around one private sector employee in twenty).

Used to work 70h/week on average, like every week of the year. I don't think I ever wworked less than 50h in a week

Re: Magistral — the first reasoning model by Mistral AI

#407

Post by Xmd5a »

algoghostf wrote: post #346
greenavocado wrote: post #208

Earlier quoted context omitted.

In the USA most software engineers are FLSA-exempt ("computer employee" exemption). No overtime pay regardless of hours worked. No legal maximum hours per day/week. No mandatory rest periods/breaks (federally). The US approach places the burden on the individual employee to negotiate protections or prove misclassification, while French law places the burden on the employer to comply with strict, state-enforced standa…

I think there is theory and there is real life. As tech worker, in 20 years career, in private sector, I have always been on forfait jours, working more than 10h/day on average, during many years weekend included. I never got paid extra hours. So I get what you say about the perception and the law. The French law is protective (i.e if I can prove that in a court I'll get my extra hours paid for sure but my career wou…

>I'll get my extra hours paid for sure but my career would end.

Are you working in an area that is that specific ? I'm French but I'm naive.

Re: Magistral — the first reasoning model by Mistral AI

#408

Post by pxc »

swah wrote: post #83
smeeth wrote: post #27

Earlier quoted context omitted.

They have a deal with Cerebras for inference. https://www.cerebras.ai/blog/mistral-le-chat

For me this is more important than quality. I love fast responses, feels more futuristic.

What are you using LLMs for?

Re: Magistral — the first reasoning model by Mistral AI

#409

Post by derefr »

ozgune wrote: post #150
danielhanchen wrote: post #3

I made some GGUFs for those interested in running them at https://huggingface.co/unsloth/Magistral-Small-2506-GGUF ollama run hf.co/unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL or ./llama.cpp/llama-cli -hf unsloth/Magistral-Small-2506-GGUF:UD-Q4_K_XL --jinja --temp 0.7 --top-k -1 --top-p 0.95 -ngl 99 Please use --jinja for llama.cpp and use temperature = 0.7, top-p 0.95! Also best to increase Ollama's context length…

Their benchmarks are interesting. They are comparing to DeepSeek-V3's (non-reasoning) December and DeepSeek-R1's January releases. I feel that comparing to DeepSeek-R1-0528 would be more fair. For example, R1 scores 79.8 on AIME 2024, R1-0528 performs 91.4. R1 scores 70 on AIME 2025, R1-0528 scores 87.5. R1-0528 does similarly better for GPQA Diamond, LiveCodeBench, and Aider (about 10-15 points higher). https://hugg…

I presume that "outdated upon release" benchmarks like these happen because the benchmark and the models in it were chosen first, before the model was created; and the model's development progress was measured using the benchmark. It then doesn't occur to anyone that the benchmark the engineers had been relying upon isn't also a good/useful benchmark for marketing upon release. From the inside view, it's just a benchmark, already there, already achieving impressive results, a whole-company internal target to hit for months — so why not publish it?

Re: Magistral — the first reasoning model by Mistral AI

#410

Post by kristianp »

redman25 wrote: post #360
jeffhuys wrote: post #334

Earlier quoted context omitted.

Could you elaborate?

Not the parent but I would say bad defaults or naming. There are countless posts from newbies wondering why a model doesn’t work as well as it should. It’s usually either because the context size is set very low by default or they didn’t realize that they weren’t running the full model (ollama uses the distilled version in place of the full version but names it after the full version). There’s also been some controve…

> ollama uses the distilled version

I've never used ollama, but perhaps you mean quantized and not distilled? Or do they actually use distilled versions?

Post reply on HN