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

Mistral AI Releases Forge

mistral.ai

Post reply on HN
Print view View original

181–190 of 210 posts

Re: Mistral AI Releases Forge

#181

Post by hermanzegerman »

brabel wrote: post #171
hermanzegerman wrote: post #137

Earlier quoted context omitted.

Where is EU protectionist? I feel we are way less protectionist than most other Economic Regions. Including the USA, which are very protectionist but always claim otherwise

Well different discussion, but look at the Mercosur agreement and all the opposition from farmers in the EU. They are extremely protectionist when it comes to agriculture, at least.

Yes the farmers are a very vocal and powerful minority.

They get more than 50% of their income from subsidies, are quite well off, but always find a reason to complain.

I was thinking more about stuff like "Buy American"-Regulations for public tenders. Stuff like that doesn't exist here

Re: Mistral AI Releases Forge

#182

Post by vincentbusch »

lol the AI-generated support reply about their own AI model is peak 2026

the naming mess is wild though. i ran into similar confusion trying to set up mistral for a side project — ended up just guessing which endpoint was the right one

Re: Mistral AI Releases Forge

#183

Post by hermanzegerman »

wqaatwt wrote: post #173
sofixa wrote: post #145

Earlier quoted context omitted.

Every company would get fined for anticompetitive behaviour, regardless of where are based.

Well yes, but because there are approximately zero EU tech companies that can be affected by these fines and regulations there is very little political pushback against them. In a certain sense it’s a way for EU to clawback at least a small slice of all that money flowing to the US.

Why should there be pushback against antitrust measures?

It's what keeps markets alive

Re: Mistral AI Releases Forge

#184

Post by prmoustache »

hermanzegerman wrote: post #181
brabel wrote: post #171

Earlier quoted context omitted.

Well different discussion, but look at the Mercosur agreement and all the opposition from farmers in the EU. They are extremely protectionist when it comes to agriculture, at least.

Yes the farmers are a very vocal and powerful minority. They get more than 50% of their income from subsidies, are quite well off, but always find a reason to complain. I was thinking more about stuff like "Buy American"-Regulations for public tenders. Stuff like that doesn't exist here

Well I can certainly understand them. Based on price tgey would not be able to compete and have half decent living wages so protectionism AND subsidies is a decent strategy to maintain local production which I feel allow a country / area to not lose a lever in international negociations.

Re: Mistral AI Releases Forge

#185

Post by WesleyJohnson »

CharlesW wrote: post #14
baby wrote: post #12

Earlier quoted context omitted.

[flagged]

[flagged]

The issue I had with RAG when I tried building our own internal chat/knowledge bot was pulling in the relevant knowledge before sending to the LLM. Domain questions like "What is Cat Block B?" are common and, for a human, provide all the context that is needed for someone to answer within our org. But vectorizing that and then finding matching knowledge produced so many false positives. I tried to circumvent that by adding custom weighting based on keywords, source (Confluence, Teams, Email), but it just seemed unreliable. This was probably a year ago and, admittedly, I was diving in head first without truly understanding RAG end to end.

Being able to just train a model on all of our domain knowledge would, I imagine, produce much better results.

Re: Mistral AI Releases Forge

#187

Post by butILoveLife »

danelski wrote: post #165
butILoveLife wrote: post #163

Earlier quoted context omitted.

You know about LMarena? I just looked it up, Mistral is number 59 on the list. Free Chinese models are better than it.

That's one of the possible benchmarks, not the only one. Being 59th there, on a list enriched with every variation of Model_Name X.Y (March 2025 Preview) Pro-Thinking , translates to being in the top 10 providers worldwide which is a very interesting mark of failure considering that coincidentally they're also number 1 from their economic area. If you don't know why the last part is important, go read some news.

[dead]

Re: Mistral AI Releases Forge

#189

Post by SyneRyder »

SyneRyder wrote: post #56
jerrygoyal wrote: post #23

Earlier quoted context omitted.

their ocr model is goated

Did they make significant improvements in OCR 3? The quality I was getting from Mistral OCR 2 was nowhere near as good as what I could get from just sending the same files to Claude Sonnet via an API call. I have been finding Voxtral useful though.

Too late to edit / update my comment, but I finally tried Mistral OCR 3 tonight on a PDF file I had. Results were good, and fast... but I actually got better quality output from sending it to Haiku 4.5 instead.

In particular, Haiku 4.5 detected some footers that were on every page and moved them to be the footer at the end of the entire document instead, so that the document read more fluently.

I imagine Mistral OCR 3 might have an edge on speed & pricing, but in my low volume / prioritizing-quality case, seems that Claude is still better than Mistral.

Re: Mistral AI Releases Forge

#190

Post by butILoveLife »

spiderfarmer wrote: post #166
butILoveLife wrote: post #132

Earlier quoted context omitted.

Grok is not SOTA, but its so obviously better than Mistral. Mistral is just some European patriotism or something. Grok is nice for asking morally gray questions. ChatGPT will lie in these cases.

> Grok is nice for asking morally gray questions. ChatGPT will lie in these cases. Are you really that oblivious to the painfully cringy manipulation tactics by the man who partied at Epstein's island? https://www.theguardian.com/technology/2025/nov/21/elon-musk...

[dead]
Post reply on HN