byte (@byteonai) header
byte (@byteonai) profile picture

one byte of ai a day. tools, repos & automations, explained simply

Joined November 2023
byte retweeted
China open-sourced a peanut-sized OCR that parses entire 100-page PDFs in one shot.. It's called Unlimited-OCR. Only 3B params. Runs locally. Every other OCR tool chops your doc into pages and loses the thread. this one reads the whole thing in a single pass. → One-shot "long-horizon" parsing (32K context window) → Multilingual, out of the box → 93% on OmniDocBench v1.5 (+6 over the DeepSeek-OCR baseline) → Edit distance stays under 0.11 past 40 pages → Runs 100% locally on your own hardware → Works with Transformers, vLLM, SGLang, and Docker Traditional cloud OCR (Textract, Google Vision, Azure Document Intelligence) often costs about $1.50–$15 per 1,000 pages. This runs on your machine. For free. Forever. Baidu built it to push DeepSeek-OCR one step further. It now has millions of downloads on Hugging Face, and most people still have no idea it exists. 100% open source (MIT). github.com/baidu/Unlimited-O…
6
12
92
5,275
China open-sourced a peanut-sized OCR that parses entire 100-page PDFs in one shot.. It's called Unlimited-OCR. Only 3B params. Runs locally. Every other OCR tool chops your doc into pages and loses the thread. this one reads the whole thing in a single pass. → One-shot "long-horizon" parsing (32K context window) → Multilingual, out of the box → 93% on OmniDocBench v1.5 (+6 over the DeepSeek-OCR baseline) → Edit distance stays under 0.11 past 40 pages → Runs 100% locally on your own hardware → Works with Transformers, vLLM, SGLang, and Docker Traditional cloud OCR (Textract, Google Vision, Azure Document Intelligence) often costs about $1.50–$15 per 1,000 pages. This runs on your machine. For free. Forever. Baidu built it to push DeepSeek-OCR one step further. It now has millions of downloads on Hugging Face, and most people still have no idea it exists. 100% open source (MIT). github.com/baidu/Unlimited-O…
6
12
92
5,275
byte retweeted
The entire RAG industry is about to get cooked. Researchers built a new RAG approach that: - needs no vector DB. - doesn't embed your data. - does zero chunking. - runs no similarity search. It's called PageIndex. Instead of chopping your docs into chunks and dumping them into Pinecone, it builds a tree index and lets the LLM reason through it like a human reading a book. hit 98.7% on FinanceBench. beat every vector RAG on the leaderboard. no embeddings. no chunking. no vector DB. 100% open source.
55
153
19
1,316
100,202
The entire RAG industry is about to get cooked. Researchers built a new RAG approach that: - needs no vector DB. - doesn't embed your data. - does zero chunking. - runs no similarity search. It's called PageIndex. Instead of chopping your docs into chunks and dumping them into Pinecone, it builds a tree index and lets the LLM reason through it like a human reading a book. hit 98.7% on FinanceBench. beat every vector RAG on the leaderboard. no embeddings. no chunking. no vector DB. 100% open source.
55
153
19
1,316
100,202
byte retweeted
China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without breaking down. just walk around with your camera and see the whole world rebuilt in 3D at 20 fps. → ~20 FPS on a single GPU → Stays stable across 10,000+ frames → Outperforms optimization-based methods on benchmarks → Handles driving footage, outdoor scenes and indoor walkthroughs 100% open source.
52
226
16
2,067
92,244
China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without breaking down. just walk around with your camera and see the whole world rebuilt in 3D at 20 fps. → ~20 FPS on a single GPU → Stays stable across 10,000+ frames → Outperforms optimization-based methods on benchmarks → Handles driving footage, outdoor scenes and indoor walkthroughs 100% open source.
52
226
16
2,067
92,244
byte retweeted
🚨DOWNLOADING ANY VIDEO FROM THE INTERNET JUST BECAME FREE AND AD-FREE someone put an open-source tool on GitHub that downloads videos from 1,800+ sites. YouTube, X, Instagram, TikTok… paste the link, pick a resolution (or mp3 audio) and done. no popups. no fake buttons. no redirects. you don't even need to install it: just run npx yoinks. it's called Yoinks. repo below.
9
105
912
33,849
This is INSANE. Google just dropped a free AI notetaker app for Mac. Every feature works without any subscription. 100% free and fully local, powered by EmbeddingGemma 2.
2
3
15
1,822
🚨DOWNLOADING ANY VIDEO FROM THE INTERNET JUST BECAME FREE AND AD-FREE someone put an open-source tool on GitHub that downloads videos from 1,800+ sites. YouTube, X, Instagram, TikTok… paste the link, pick a resolution (or mp3 audio) and done. no popups. no fake buttons. no redirects. you don't even need to install it: just run npx yoinks. it's called Yoinks. repo below.
9
105
912
33,849
byte retweeted
Microsoft killed the GPU mafia 🤯 They open-sourced bitnet.cpp, their 1-bit LLM inference framework. It can run a 100B-parameter BitNet model on a single CPU, no GPU needed. - Up to 6.17x faster on x86 CPUs - Up to 82.2% less energy 100% Open Source. github.com/microsoft/BitNet
101
294
24
2,030
619,182
Microsoft killed the GPU mafia 🤯 They open-sourced bitnet.cpp, their 1-bit LLM inference framework. It can run a 100B-parameter BitNet model on a single CPU, no GPU needed. - Up to 6.17x faster on x86 CPUs - Up to 82.2% less energy 100% Open Source. github.com/microsoft/BitNet
101
294
24
2,030
619,182
follow me for more! I’m post the best AI tools, workflows and open-source tools daily.
2
9
12,825
🚨 BREAKING: ChatGPT has a feature called "language learning mode". You can use it to learn any language from scratch, like having a private tutor that would normally cost $1,000. Here are 7 prompts to turn it on:
2
2
28
4,540
7. Spaced-repetition review 'Based on the [language] I've been learning, create quick review quizzes that mix old and new vocabulary, including cloze tests and two-way translations. At the end, tell me which points I still need to strengthen.'
1
2
174
If you found this thread useful: 1. Follow me 2. Repost the first tweet so more people see it Thank you for the support!
1
136