Magistral — the first reasoning model by Mistral AI • Hacker News Board

Re: Magistral — the first reasoning model by Mistral AI

#441

Post by CMay » Sat, Jun 14, 2025, 7:12 PM UTC

staticman2 wrote: post #435

CMay wrote: post #353

Earlier quoted context omitted.

Not going to leak my tests, but here's how you can create your own. - Think up a topic that's interesting to you, yet maybe controversial. - Look up primary sources and empirical information about it. - Then look at a relevant Wikipedia article about it to see if the way the Wikipedia article frames it is honestly and faithfully justified by the primary sources and empirical data about it. If the article seems to hav…

I don't get it. If I think that Rabbits and Hares are classified by Wikipedia incorrectly and Ideological Wikipedia Editors are hiding the truth with Disinformation, why would I give the model any credit if it tells the correct answer only if I develop a custom 22 point mammalian biology reasoning checklist that leads it to the Real Truth about Rabbits and Hares? It certainly doesn't inspire confidence that any other…

That would be a bad checklist and overspecialized. You want it to be as generally applicable as possible.

Re: Magistral — the first reasoning model by Mistral AI

#442

Post by jama211 » Sat, Jun 14, 2025, 7:13 PM UTC

alienbaby wrote: post #237

distortionfield wrote: post #186

Earlier quoted context omitted.

You’re being downvoted but you’re right. The number of people who act like a web cam reproduces the in person experience perfectly, for good and bad, is hilarious to me.

I think the mistake people make is believing that one approach is best for all. Diffferent people work most effectively in different ways.

Well said. If you make me commute to an office I’m far far far less productive, simple as that.

Re: Magistral — the first reasoning model by Mistral AI

#443

Post by bobxmax » Sat, Jun 14, 2025, 11:27 PM UTC

micromacrofoot wrote: post #433

bobxmax wrote: post #274

Earlier quoted context omitted.

A 200B economy growing 2% is the future of the EU? Yes that is the point I am making.

How much is an economy supposed to grow?

Bangladesh has twice the GDP and 3x the growth. How long do you expect Portugal to be relevant?

Re: Magistral — the first reasoning model by Mistral AI

#444

Post by swah » Mon, Jun 16, 2025, 12:35 PM UTC

pxc wrote: post #436

swah wrote: post #431

Earlier quoted context omitted.

Mostly "How is $term in English", what is $thing, review this message for clarity, clean up this data, parse this screenshot, and coding.

I see! So for these, you tend to find the accuracy "good enough" on the faster-but-less-accurate models. I generally find the same thing for simple definitions/translations and other "chat" tasks. I'm a little bit surprised that you also find it so for coding, but otherwise I think I get it.

Oh no, for coding I probably use Claude inside Cursor and switch tabs....