themanmaran
- Karma
- 0
- Created
- ()
- Submissions
- 0
- The Process Is the Product (tylermaran.substack.com)
- JavaScript Demos in 140 Characters (beta.dwitter.net)
-
https://status.openai.com/
- OmniAI (YC W24) Is Hiring Forward Deployed Engineers (ycombinator.com)
- Weightlifting Tracker for Coders (github.com)
- OpenAI releases image generation in the API (openai.com)
- JavaScript Demos in 140 Characters (dwitter.net)
-
Last week was big for open source LLMs. We got: - Qwen 2.5 VL (72b and 32b) - Gemma-3 (27b) - DeepSeek-v3-0324 And a couple weeks ago we got the new mistral-ocr model. We updated our OCR benchmark to include the new…
- Benchmarking open source VLMs for OCR (getomni.ai)
- Show HN: Benchmarking VLMs vs. Traditional OCR (getomni.ai)
Vision models have been gaining popularity as a replacement for traditional OCR. Especially with Gemini 2.0 becoming cost competitive with the cloud platforms. We've been continuously evaluating different models since…
- Fine Tuning on Synthetic Documents (getomni.ai)
- Infinite PDF Generator (getomni.ai)
-
Saw a ShowHN post [0] today about an open source document extractor tool. I thought the workflow sounded pretty similar to our library, and only to realize it's a direct rip of Zerox [1]. Looking through the code: 1.…
- Show HN: Zerox v1 – Document OCR with GPT-vision (getomni.ai)
Hey everyone! Today we're launching the stable release of Zerox, our open source OCR tool we've been building at OmniAi. This started out as a weekend hack with gpt-4-mini, using the very basic strategy of "just ask the…
- Show HN: What's HN Working On – A structured dataset (github.com)
The latest Ask HN: What are you working[1] on thread just dropped. And to give my own answer, building structured datasets! I wrote a quick scraper for the HN comments. Just pulling every top level comment along with…
- Show HN: Zerox – Document OCR with GPT-mini (github.com)
This started out as a weekend hack with gpt-4-mini, using the very basic strategy of "just ask the ai to ocr the document". But this turned out to be better performing than our current implementation of…
- OmniAI (YC W24) Is Hiring a Founding Engineer in SF (workatastartup.com)
- “Hallucination” is integral to thought (getomni.ai)
- “Hallucination” is part of thought (getomni.ai)
- Think of your LLM as a User (getomni.ai)
- Treat the AI Like a User (getomni.ai)
- Mars will have a lot of wicker furniture (havewelanded.com)