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

Mistral OCR

mistral.ai

Post reply on HN
Print view View original

61–70 of 450 posts

Re: Mistral OCR

#61

Post by notepad0x90 »

devmor wrote: post #20
notepad0x90 wrote: post #16

I was just watching a science-related video containing math equations. I wondered how soon will I be able to ask the video player "What am I looking at here, describe the equations" and it will OCR the frames, analyze them and explain them to me. It's only a matter of time before "browsing" means navigating HTTP sites via LLM prompts. although, I think it is critical that LLM input should NOT be restricted to verbal…

Good lord, I dearly hope not. That sounds like a coddled hellscape world, something you'd see made fun of in Disney's Wall-E.

hence my comment about privacy and need for legislation :)

It isn't the tech that's the problem but the people that will abuse it.

Re: Mistral OCR

#63

Post by jslezak »

Has anyone tried it for handwriting?

So far Gemini is the only model I can get decent output from for a particular hard handwriting task

Re: Mistral OCR

#64

Post by salynchnew »

cxie wrote: post #40

The new Mistral OCR release looks impressive - 94.89% overall accuracy and significantly better multilingual support than competitors. As someone who's built document processing systems at scale, I'm curious about the real-world implications. Has anyone tried this on specialized domains like medical or legal documents? The benchmarks are promising, but OCR has always faced challenges with domain-specific terminology…

Also interesting to see that parts of the training infrastructure to create frontier models is itself being monetized.

Re: Mistral OCR

#65

Post by kergonath »

themanmaran wrote: post #46
ChemSpider wrote: post #27

"World's best OCR model" - that is quite a statement. Are there any well-known benchmarks for OCR software?

We published this benchmark the other week. We'll can update and run with Mistral today! https://github.com/getomni-ai/benchmark

Excellent. I am looking forward to it.

Re: Mistral OCR

#67

Post by notepad0x90 »

groby_b wrote: post #31
notepad0x90 wrote: post #16

I was just watching a science-related video containing math equations. I wondered how soon will I be able to ask the video player "What am I looking at here, describe the equations" and it will OCR the frames, analyze them and explain them to me. It's only a matter of time before "browsing" means navigating HTTP sites via LLM prompts. although, I think it is critical that LLM input should NOT be restricted to verbal…

Now? OK, you need to screencap and upload to LLM, but that's well established tech by now. (Where by "well established", I mean at least 9 months old ;) Same goes for "navigating HTTP sites via LLM prompts". Most LLMs have web search integration, and the "Deep Research" variants do more complex navigation. Video chat is there partially, as well. It doesn't really pay much attention to gestures & expressions, but I'd…

Yeah, all these things are possible today, but getting them well polished and integrated is another story. Imagine all this being supported by "HTML6" lol. When apple gets around to making this part of safari, then we know it's ready.

Re: Mistral OCR

#68

Post by pqdbr »

I tried with both PDFs and PNGs in Le Chat and the results were the worst I've ever seen when compared to any other model (Claude, ChatGPT, Gemini).

So bad that I think I need to enable the OCR function somehow, but couldn't find it.

Re: Mistral OCR

#69

Post by sunami-ai »

Making Transformers the same cost as CNN's (which are used in character-level ocr, as opposed to image-patch-level) is a good thing. The problem with CNN based character-level OCR is not the recognition models but the detection models. In a former life, I found a way to increase detection accuracy, and, therefore, overall OCR accuracy, and used that as an enhancement on top of Amazon and Google OCR. It worked really well. But the transformer approach is more powerful and if it can be done for $1 per 1000 pages, that is a game changer, IMO, at least of incumbents offering traditional character-level OCR.

Re: Mistral OCR

#70

Post by cxie »

unboxingelf wrote: post #47
cxie wrote: post #40

The new Mistral OCR release looks impressive - 94.89% overall accuracy and significantly better multilingual support than competitors. As someone who's built document processing systems at scale, I'm curious about the real-world implications. Has anyone tried this on specialized domains like medical or legal documents? The benchmarks are promising, but OCR has always faced challenges with domain-specific terminology…

We’ll just stick LLM Gateway LLM in front of all the specialized LLMs. MicroLLMs Architecture.

I actually think you're onto something there. The "MicroLLMs Architecture" could mirror how microservices revolutionized web architecture.

Instead of one massive model trying to do everything, you'd have specialized models for OCR, code generation, image understanding, etc. Then a "router LLM" would direct queries to the appropriate specialized model and synthesize responses.

The efficiency gains could be substantial - why run a 1T parameter model when your query just needs a lightweight OCR specialist? You could dynamically load only what you need.

The challenge would be in the communication protocol between models and managing the complexity. We'd need something like a "prompt bus" for inter-model communication with standardized inputs/outputs.

Has anyone here started building infrastructure for this kind of model orchestration yet? This feels like it could be the Kubernetes moment for AI systems.

Post reply on HN