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

331–340 of 444 posts

Re: Magistral — the first reasoning model by Mistral AI

#331

Post by MindTheAbstract »

LordDragonfang wrote: post #269
cluckindan wrote: post #242

Earlier quoted context omitted.

It does not do any thinking. It is a statistical model, just like the rest of them.

"Thinking" is a term of art referring to the hidden/internal output of "reasoning" models where they output "chain of thought" before giving an answer[1]. This technique and name stem from the early observation that LLMs do better when explicitly told to "think step by step"[2]. Hope that helps clarify things for you for future constructive discussion. [1] https://arxiv.org/html/2410.10630v1 [2] https://arxiv.org/pdf…

I know this is the terminology, but I'd argue that the activations are the actual thinking. It's probably too late to change that, but I wish people would refer to thinking as the work Anthropic and Deepmind are doing with their mech interp

Re: Magistral — the first reasoning model by Mistral AI

#332

Post by MindTheAbstract »

asadotzler wrote: post #283
ACCount36 wrote: post #230

Earlier quoted context omitted.

>with the technology plateau-ing People were claiming that since year 2022. Where's the plateau?

The pre-training plateau is real. Nearly all the improvements since then have been around fine tuning and reinforcement learning, which can only get you so far. Without continued scaling in the base models, the hope of AGI is dead. You cannot reach AGI without making the pre-training model itself a whole lot better, with more or better data, both of which are in short supply.

While I tend to agree, I wonder if synthetic data might be reaching a new high with concepts like Google's AlphaEvolve. It doesn't cover everything, but at least in verifiable concepts, I could see it produce more valuable training data. It's a little unclear to me where AGI will come from (LLMs? EBMs - @LeCun)? Something completely different?)

Re: Magistral — the first reasoning model by Mistral AI

#334

Post by jeffhuys »

otabdeveloper4 wrote: post #323
diggan wrote: post #166

Earlier quoted context omitted.

Ollama doesn't like proper naming for some reason, so `ollama pull magistral:latest` lands you with the q4_K_M version (currently, subject to change). Mistral's API defaults to `magistral-medium-2506` right now, which is running with full precision, no quantization.

Nobody should be ever using ollama, for any reason. It literally only makes everything worse and more convoluted with zero benefits.

Could you elaborate?

Re: Magistral — the first reasoning model by Mistral AI

#335

Post by psychoslave »

kgwgk wrote: post #271
Saline9515 wrote: post #235

Earlier quoted context omitted.

Everyone is "forfait cadre", which allow them to work with no practical time limit since they don't log their time spent at work. https://www.service-public.fr/particuliers/vosdroits/F19261

It seems that 20% of employees in the private sector are "cadres" and half of them are on "forfait jours". That makes around 10% of the private sector employees working 218 days per year without the 48/44 weekly hour limits. It's more than I thought but I doubt that many of them work more than 10 hours per day. Whether that's "exceptional" or not is a matter of definition, of course.

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.

Re: Magistral — the first reasoning model by Mistral AI

#336

Post by cluckindan »

jeffhuys wrote: post #333
cluckindan wrote: post #326

Earlier quoted context omitted.

Human neurons are not reducible to arithmetic artificial neurons in a statistical model. Do not conflate them.

Why not, actually?

Because we do not have a complete understanding of human neurons. How are we supposed to accurately model something we cannot directly observe?

Re: Magistral — the first reasoning model by Mistral AI

#337

Post by Agraillo »

FabHK wrote: post #316

So, is it accessible in Le Chat?

From the release "..You can try out a preview version of Magistral Medium in Le Chat..", I suppose it's when the drop down in "Thinking" mode is either slow or fast (limited to 3 queries per day).

My favorite from the last months was asking for a string that for base64 produces strings with non-alphanumeric and non-padding symbols (so '+' or '/' should be in the output). It thought for 7 minutes and 74k of markdown length, and finally came up with the AB?C string that produces QUI/Qw== (correct). It is impressive, because general LLMs just always fail, but I didn't try other "thinking" models recently.

Re: Magistral — the first reasoning model by Mistral AI

#338

Post by TheDong »

cluckindan wrote: post #336
jeffhuys wrote: post #333

Earlier quoted context omitted.

Why not, actually?

Because we do not have a complete understanding of human neurons. How are we supposed to accurately model something we cannot directly observe?

Do you also complain when someone says "Half-life 2 has great water-physics" with "Don't call it physics, we still don't understand all the physical laws of the universe, and also they use limited-precision floating-point, so it's not water-physics, it's just a bunch of math"?

Like, we've agreed that "water-physics" and "cloth physics" in 3d graphics refers to a mathematical approximation of something we don't actually understand at the subatomic level (are there strings down there? Who knows).

Can "thinking" in AI not refer to this intentionally false imitation that has a similar observable outward effect?

Like, we're okay saying minecraft's water has "water physics", why are we not okay saying "in the AI context, thinking is a term that externally looks a bit like a human thinking, even though at a deeper layer it's unrelated"?

Or is thinking special, is it like "soul" and we must defend the word with our life else we lose our humanity? If I say "that building's been thinking about falling over for 50 years", did I commit a huge faux pas against my humanity?

Re: Magistral — the first reasoning model by Mistral AI

#339

Post by CMay »

One immediate observation I have about this model is that it seems to do a better job of filtering out or toning down some ideological disinformation that other models regurgitate from activist controlled Wikipedia articles, at least for a few I've checked. Previously you had to write your own sanity-check prompts to get the model to do extra up-front work to validate the logical and historical accuracy of things before it spits out what it thinks is the most popular answer.

With this, at least it seems like some of that work was done upfront or the thinking is tuned to avoid those issues, because it's giving me similar conclusions to a sanity-checked prompt. Heck, even Google Gemini and ChatGPT were spitting that stuff out, where this one is giving me a reasonable response. So in that regard, big thumbs up to the Mistral team if they did any specific work in that area. It's something I cared about that I was getting concerned nobody else cared about enough to fix.

Re: Magistral — the first reasoning model by Mistral AI

#340

Post by boredhedgehog »

cluckindan wrote: post #242
fzzzy wrote: post #223

Earlier quoted context omitted.

My impression from running the first R1 release locally was that it also does too much thinking.

It does not do any thinking. It is a statistical model, just like the rest of them.

These kind of comments are the equivalent of going to dog owners' forums, analyzing word choices in every post and warning the dog owners about the dangers of anthropomorphizing their pets, an effort as accurate as it is boorish and ineffectual.
Post reply on HN