Viewing profile — kbyatnal

agreed! dogfooding is the best — we'll integrate this into our core product, which will force us to improve it very quickly

Your issues are mostly with the file picker, which is a brand new component that was just added yesterday in response to a feature request after launch: https://x.com/andrewlu0/sta…

We're open-sourcing 14 components & examples today for PDF, DOCX, and XLSX viewers, plus bounding box citations, file upload, e-signature, and more. It's MIT licensed and fully cus…

Deepseek OCR is no longer state of the art. There are much better open source OCR models available now. ocrarena.ai maintains a leaderboard, and a number of other open source optio…

Ultimately, there’s some intersection of accuracy x cost x speed that’s ideal, which can be different per use case. We’ll surface all of those metrics shortly so that you can pick …

Claude coming shortly (in the next ~1 hour)

We wanted to keep the focus on (1) foundation VLMs and (2) open source OCR models. We had Mistral previously but had to remove it because their hosted API for OCR was super unstabl…

Sonnet/Opus is being added shortly!

I built OCR Arena as a free playground for the community to compare leading foundation VLMs and open-source OCR models side-by-side. Upload any doc, measure accuracy, and (optional…

Yeah that can occasionally work and something we've tested, but it introduces a lot of noise unfortunately and makes systematic evals difficult.

School transcripts are surprisingly one of the hardest documents to parse. The thing that makes them tricky is (1) the multi-column tabular layouts and (2) the data ambiguity. Tran…

thanks! Datalab is great, I've met Vik a few times and their team has done some impressive work. We can also support the conversion to markdown use case, and might be a better fit …

It's very dependent on the use case. That's why we offer a native evals experience in the product, so you can directly measure the % accuracy diffs between the two modes for your e…

Exactly correct! We've had users migrate over from other providers because our granular pricing enabled new use cases that weren't feasible to do before. One interesting thing we'v…

Feedback heard. Pricing is hard, and we've iterated on this multiple times so far. Our goal is to provide customers with as much transparency & flexibility as possible. Our pricing…

good question! Our goal is to provide customers with as much flexibility as possible. For certain use cases, you might be willing to take a slight hit to accuracy in exchange for b…

thanks! A lot of customers choose us for our handwriting, checkbox, and table performance. To handle complex handwriting, we've built an agentic OCR correction layer which uses a V…

There's certainly a lot of tools that focus on individual parts of the problem (e.g. the OCR layer, or workflows on top). But very few that solve the problem end-to-end with enough…

thanks! Yup that's correct, we offer a set of APIs for handling documents: parsing, classification, splitting, and extraction. We've seen customers integrate these in a few interes…

There's definitely no shortage of options. OCR has been around for decades at this point, and legacy IDP solutions really proliferated in the last ~10 years. The world today is qui…

thank you Fabio!

Hey HN! We’re Kushal and Eli, co-founders of Extend ( https://www.extend.ai/ ). Extend is a toolkit for AI teams to ingest any kind of messy document (e.g. PDFs, images, excel file…