Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

launching our open source OCR tool today! try it out with some terrible pdfs and let me know how it goes:

Tyler Maran

1,540 subscribers

342,717 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji Eğitim

Anya Rossi• Live Now

Private livecam show

10 Yorum

Karthik Kannan profil fotoğrafı

Karthik Kannan1 yıl önce

how are you dealing with hallucinations in the text if you're using GPT to OCR the text? while great for some use cases i've noticed hallucinations when it comes to dense text at scale. is there some benchmarks you're comparing against

Tyler Maran profil fotoğrafı

Tyler Maran1 yıl önce

hey Karthik. we're working pretty hard on a benchmark right now. Noticed the same issues with dense text (sideway text too). It's one of the big steps we need to take as we start on a fine tuning dataset. I'll be sharing as we make progress!

Bryan Lee profil fotoğrafı

Bryan Lee1 yıl önce

Waited a few minutes and nothing happened.

Tyler Maran profil fotoğrafı

Tyler Maran1 yıl önce

hey Bryan! sorry got more traffic than we expected and we had to up our limits. should be good to go now!

Dan Manastireanu profil fotoğrafı

Dan Manastireanu1 yıl önce

You should check out General OCR Theory, a specialized llm for OCR 2.0 Unfortunately, they don't have a gpt-4o benchmark for comparisson, but the results are pretty impressive

Daniel Tenner profil fotoğrafı

Daniel Tenner1 yıl önce

@ycombinator I’m literally just about to implement structured document OCR for accounts, tax computations and other similar docs, for my biz’s internal CRM. I thought “oh great I’ll use this instead of Textract”. But I can’t because of the “book a demo” thing. And no pricing. 😕

Harshil Prajapati profil fotoğrafı

Harshil Prajapati1 yıl önce

@ycombinator Make it open source

Tyler Maran profil fotoğrafı

Tyler Maran1 yıl önce

@ycombinator ... it is open source 👆

Tom Osman 🐦‍⬛ profil fotoğrafı

Tom Osman 🐦‍⬛1 yıl önce

trying now with some different one's but doesn't seem to be working? Using Arc if that helps at all.

Tyler Maran profil fotoğrafı

Tyler Maran1 yıl önce

we got a lot of traffic and had to up our limits! should be good to go now!

Benzer Videolar

Someone try this and let me know how it turns out

Someone try this and let me know how it turns out

Clown World ™ 🤡

226,603 görüntüleme • 5 ay önce

End of the weekend built this invoice builder using bolt.new and Supabase Used supabase edge functions to send emails (didn’t know bolt could handle that so well!) Still figuring out how to generate exact PDFs based on selected templates if you know any good libraries let me know in comments. Planning to open source it soon after a few more fixes and features let me know if you’d like to try it out!

End of the weekend built this invoice builder using bolt.new and Supabase Used supabase edge functions to send emails (didn’t know bolt could handle that so well!) Still figuring out how to generate exact PDFs based on selected templates if you know any good libraries let me know in comments. Planning to open source it soon after a few more fixes and features let me know if you’d like to try it out!

Dhruval

55,006 görüntüleme • 1 yıl önce

🚨🤖 Today, I'm launching an AI agent that gets things done across iPhone apps. It's powered by OpenAI GPT 4.1 and is open source. Try it out!

🚨🤖 Today, I'm launching an AI agent that gets things done across iPhone apps. It's powered by OpenAI GPT 4.1 and is open source. Try it out!

Rounak Jain

170,225 görüntüleme • 1 yıl önce

Try Yoga 🧘‍♀️ with heels 👠 Let me know how it goes ha 😂😂😜😜❤️‍🔥🥰🫶🔥

Try Yoga 🧘‍♀️ with heels 👠 Let me know how it goes ha 😂😂😜😜❤️‍🔥🥰🫶🔥

grannygenes

19,493 görüntüleme • 12 gün önce

Shuuuu this is a tough one, but truuussst me you’ll feel really good and accomplished after smashing it! Try out this Functional Workout and let me know how it goes! 🫶🏾🙌🏾 Song: LaTique - Sawela #ShedKilosWithPhume #Team5am #FetchYourBody2025

Shuuuu this is a tough one, but truuussst me you’ll feel really good and accomplished after smashing it! Try out this Functional Workout and let me know how it goes! 🫶🏾🙌🏾 Song: LaTique - Sawela #ShedKilosWithPhume #Team5am #FetchYourBody2025

Phume

31,204 görüntüleme • 1 yıl önce

The new editor is live! Build any page layout as easily as dragging things around, and get an automatically responsive website that you can publish instantly. Try it out and let me know how it goes.

The new editor is live! Build any page layout as easily as dragging things around, and get an automatically responsive website that you can publish instantly. Try it out and let me know how it goes.

Hernán Sartorio

69,886 görüntüleme • 1 yıl önce

I made a thing --> A visual builder to help you master that one-shot prompt, so give it a try and let me know how it goes 👇

I made a thing --> A visual builder to help you master that one-shot prompt, so give it a try and let me know how it goes 👇

Paul Gosnell

38,359 görüntüleme • 1 yıl önce

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

Everyone is sleeping on this new OCR model! dots-ocr is a new 1.7B vision-language model that achieves SOTA performance on multilingual document parsing. - Supports 100+ languages - Works with both images and PDFs - Handles text, tables, formulas seamlessly 100% open-source.

Akshay 🚀

252,074 görüntüleme • 10 ay önce

Today we're launching Paxel: a free tool that analyzes your Claude, Codex, and Cursor coding sessions and gives you a profile of how you build with AI. It runs locally inside Docker, and your code never leaves your machine. Try it at

Y Combinator

586,432 görüntüleme • 1 ay önce

You can now chat locally with AI and your PDFs completely offline. Blueshell runs in your browser and doesn't communicate with any server. No installation and open source. Here's how to access it:

You can now chat locally with AI and your PDFs completely offline. Blueshell runs in your browser and doesn't communicate with any server. No installation and open source. Here's how to access it:

Paul Couvert

42,331 görüntüleme • 1 yıl önce

Yasyf Mohamedali and I built Summ, an open-source tool that provides intelligent search and question-answering across large sets of transcripts. ⚡️ We turn your unstructured transcripts into queryable SQL and JSON! Try it out and read how we did it here:

Yasyf Mohamedali and I built Summ, an open-source tool that provides intelligent search and question-answering across large sets of transcripts. ⚡️ We turn your unstructured transcripts into queryable SQL and JSON! Try it out and read how we did it here:

Markie Wagner

54,646 görüntüleme • 3 yıl önce

Today I’m launching Open Interpreter, an open-source Code Interpreter that runs locally. Summarize PDFs, visualize datasets, and control your browser — all from a ChatGPT-like interface in your terminal. ● $ pip install open-interpreter $ interpreter

Today I’m launching Open Interpreter, an open-source Code Interpreter that runs locally. Summarize PDFs, visualize datasets, and control your browser — all from a ChatGPT-like interface in your terminal. ● $ pip install open-interpreter $ interpreter

killian

2,055,579 görüntüleme • 2 yıl önce

I’ll let you know how it goes

I’ll let you know how it goes

Husk

369,346 görüntüleme • 2 ay önce

OMG! YES! 🥳 We just went totally BANANAS 🍌 with our new image retouch tool! You HAVE to try it! It's available NOW at Trust me, you're going to love it! 😉 Let me know what masterpieces you create! 🎨

OMG! YES! 🥳 We just went totally BANANAS 🍌 with our new image retouch tool! You HAVE to try it! It's available NOW at Trust me, you're going to love it! 😉 Let me know what masterpieces you create! 🎨

Lia

11,627 görüntüleme • 10 ay önce

You don't need to pay $200 for AI. We're launching Open Operator - an open source reference project that shows how easy it is to add web browsing capabilities to your existing AI tool. It's early, slow, and might not work everywhere. But it's free and open source! 🔗👇

You don't need to pay $200 for AI. We're launching Open Operator - an open source reference project that shows how easy it is to add web browsing capabilities to your existing AI tool. It's early, slow, and might not work everywhere. But it's free and open source! 🔗👇

Paul Klein IV

349,171 görüntüleme • 1 yıl önce

🚨 Introducing Dragula 🧛‍♂️ An idiot-proof drag-and-drop engine for SwiftUI. A lot of you asked me to open source it - so here you go :) Try it. Break it. Let me know! I’ll be building and open-sourcing more fun tools like this. Follow along for the ride! 🛠️

🚨 Introducing Dragula 🧛‍♂️ An idiot-proof drag-and-drop engine for SwiftUI. A lot of you asked me to open source it - so here you go :) Try it. Break it. Let me know! I’ll be building and open-sourcing more fun tools like this. Follow along for the ride! 🛠️

Mustafa Yusuf

116,508 görüntüleme • 1 yıl önce

New prototype for my horde shooter up on Itch, now with some actual UI! Try it out and let me know what you think :) Link in the reply ⬇️ #gamedev #indiedev

New prototype for my horde shooter up on Itch, now with some actual UI! Try it out and let me know what you think :) Link in the reply ⬇️ #gamedev #indiedev

taikwy

15,866 görüntüleme • 11 ay önce

One Galandra isn't enough for you? Let her multiply thanks to the echoes of time. ⏳ Try the Mania Ordeal and let us know how it goes!

One Galandra isn't enough for you? Let her multiply thanks to the echoes of time. ⏳ Try the Mania Ordeal and let us know how it goes!

Absolum | Now Available on XBOX!

18,831 görüntüleme • 4 ay önce

Don’t worry KALYJAY 😁… Try it out and let me know if it works🫠. SPREADING TECH WISDOM EVERYWHERE 🚀❤️

Don’t worry KALYJAY 😁… Try it out and let me know if it works🫠. SPREADING TECH WISDOM EVERYWHERE 🚀❤️

areyouAgod?

287,256 görüntüleme • 1 yıl önce