dar8919

https://mistral.ai/news/mistral-ocr , recent release. Its been a step function improvement for my pipelines

Curious why open source? At the end of the day, lead gen is mostly about data curation. You’re either paying for access to curated feeds or spending time/money building your own pipeline.

Can you share more about how it compares with other popular tools in this space? Very hard to tell from your homepage

Wow, shows very good performance on my wikipedia dataset. Incredible that companies are open sourcing so much good stuff. Hope this trend continues.

Thanks for the example and that sounds really solid cost savings and definitely agree with the trend that it is here to stay.

For invoice parsing (various formats), are you just using GPT4V? When GPT4V initially came out, i benchmarked it against an out of the box invoice parser from Google Cloud (https://cloud.google.com/document-ai) on 16 documents and it was much better accuracy wise. For ex: i'd get results parsing 10,100 as 101100 (no comma).

Curious if you saw problems like this in your pipeline or if its gotten much better since?

Love it!

Hi HN! I recently came across an really impressive 3D animation on Sustainable Horizons website: https://sustainablehorizons.ai/ (I have no affiliation)

The level of detail is so good. Website claims using Generative AI (and three.js).

I was curious if anyone had pointers on how something a AI-powered 3D animation authoring workflow would look like. Any guidance or pointers would be greatly appreciated!

Yup, looks down again =/

Back up now

Both.

When it comes to technology, I find books to be a secondary citizen. If I look at things I know and use in my day job. Things like stack overflow, blog posts and reading man pages have been my primary knowledge sources.

But off late, I've been reading books and mostly enjoying the titles I've read. But the biggest problem for me is finding my next book.

Amazon mostly recommends titles very closely related to what I've purchased, and I haven't had much success with goodreads lists. So I'm curious how HN users find their next book.

North of 20M $

Evernote

The second code snippet looks wrong,

write(out, buf, (r - w)) should be write(out, buf + w, r - w)

Vim

Jimmy Wales, Wikipedia