kbyatnal
Joined 10 years ago
Karma
2,179
Submissions
222
Member since
Mar 23
building extend.ai
View on Hacker NewsRecent submissions
Comment · 23 days ago
thanks!
Comment · 23 days ago
A24 (the studio behind the movie) is one of our customers, so we're hosting a watch party in SF
plus, we used our APIs to parse all the theranos PDFs to power the experience
hope our content marketing made your day a bit more fun!
Comment · 23 days ago
there's too many easter eggs to count, I didn't even realize that one existed
Comment · 23 days ago
we parsed all the theranos PDF filings with Extend (https://extend.ai/) and wanted a fun interactive way of visualizing them!
Comment · 4 months ago
agreed! dogfooding is the best — we'll integrate this into our core product, which will force us to improve it very quickly
Comment · 4 months ago
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/status/2064726998186971400?s=46
It has some rough edges as a result, but your suggestions are very valid. We’ll make those improvements (we’re also taking PRs!).
Comment · 8 months ago
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 options like dots [1] or olmOCR [2] rank higher.
Comment · 11 months ago
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 the best model for the job along those axes.
Comment · 11 months ago
Claude coming shortly (in the next ~1 hour)
Comment · 11 months ago
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 unstable and returned a lot of garbage results unfortunately.
Paddle, Nanonets, and Chandra being added shortly!