Remote: Yes

Willing to relocate: Yes!

Technologies: Python, Kubernetes, Java, Aws, ML and much more

Résumé/CV: https://drive.google.com/file/d/1pOH2OhfHTgKLq34u1JlzZV723bR...

Email: elias.thouant@gmail.com

That a super impressive! I wonder how that would be at scale, with a few millions people. I’m don’t think that would remain as accurate

I think this explanation is true but incomplete. I believe it's also related to Critical Flicker Fusion Frequency [0], the way I see it, if an organism is smaller it has a higher frequency, it sees more image per second, therefore perception of time is slower. (E.g. a fly sees you moving really slowly). Maybe it's related to the processing time of images, with smaller brains insect can process more of them per second.

Maybe humans process more images as children, therefore see the time time going slower.

It's been a while I didn't think about this, maybe some studies have been made in the past years.

[0] https://en.wikipedia.org/wiki/Flicker_fusion_threshold

Little typo, looking at the link it's 11.2 not 13.2. Someone knows why this peak?

That's when I thought: What if I use multiple LLMs and take the most common response to improve accuracy?

This idea became this new project. You provide your documents, an SQLModel schema, an LLM provider, plus what you'd like to extract and Extrai does the rest. Including storing them in a DB afterwards.

There are a few other features such as SQLModel generation based on your documents, hierarchical extraction to manage nested objects more efficiently and built-in analytics.

Feedback is more than welcomed, since it's still a work in progress!

I built a landing page for people interested in a managed solution (I also had fun with threeJS!)

Let me know what you think

Landing page: extrai.xyz Github: https://github.com/Telsho/Extrai

Comments URL: https://news.ycombinator.com/item?id=45803134

Points: 5

# Comments: 0