It’s far more effective to run AI locally where it can read and edit your config, so we suggest that in the docs instead.
OPEN SOURCE
-
Open Source Project Credits and Support Offer
By
–
what are you building? if it’s open source happy to grant some credits 🙂
-
Google’s AI debates itself without training
By
–
HOLY SHIT… Google just proved that reasoning models aren't thinking, they're arguing. > DeepSeek-R1 spontaneously generates internal multi-agent debates inside its own chain of thought. Nobody trained it to do this. Reinforcement learning for accuracy produced it
-
Open-source models for agent tools over closed APIs
By
–
It’s time for open-source agent tools to rely primarily on open-source models, instead of closed-source APIs that send all your data to the cloud and ultimately will get hacked and/or shut down
-
daVinci-MagiHuman: Fast audio-video generation transformer model released
By
–
daVinci-MagiHuman is here: 15B single-stream Transformer for joint audio-video generation. 🎬 Demo video👇
— ModelScope (@ModelScope2022) 30 mars 2026
⚡ Blazing fast: 5s 256p video in 2s, 1080p in 38s — single H100
🎯 80.0% win rate vs Ovi 1.1, 60.9% vs LTX 2.3 (2,000 pairwise evals)
✅ WER 14.60% — best-in-class… pic.twitter.com/6GuiOTtedtdaVinci-MagiHuman is here: 15B single-stream Transformer for joint audio-video generation. 🎬 Demo video👇 ⚡ Blazing fast: 5s 256p video in 2s, 1080p in 38s — single H100 🎯 80.0% win rate vs Ovi 1.1, 60.9% vs LTX 2.3 (2,000 pairwise evals) ✅ WER 14.60% — best-in-class audio-visual sync, beats LTX 2.3 (19.23%) and Ovi 1.1 (40.45%) 📚 6 languages: Mandarin, Cantonese, EN, JP, KR, DE, FR 🧠 One unified stream: text + video + audio tokens, self-attention only. 🛠️ Full stack open: base + distilled (8-step, CFG-free) + super-res + inference code 📄 Apache 2.0. 🤖: modelscope.cn/models/GAIR/da… 💻: github.com/GAIR-NLP/daVinci-…
→ View original post on X — @shiqi_yang_147, 2026-03-30 09:18 UTC
-
Real-time Pose Matching Game Built on Metis Blockchain
By
–
Community member Dilip.m built a real-time pose matching game on Metis. Show a famous film pose (Karate Kid, Usain Bolt, Rocky), match it with your body, and the image reveals when you nail it. YOLOv8-pose, cosine similarity, fully on-device. #EdgeAI 🕺 eu1.hubs.ly/H0t21zZ0
→ View original post on X — @axeleraai, 2026-03-30 08:30 UTC
-
PaddleOCR Surpasses Tesseract as Most-Starred OCR Project
By
–
PaddleOCR has surpassed 73.3K stars on GitHub—overtaking Google’s Tesseract (73.2K) to become the most-starred OCR project globally. GitHub: https://
github.com/PaddlePaddle/P
addleOCR
… PP-OCRv5: https://
arxiv.org/pdf/2603.24373 PaddleOCR-VL: https://
arxiv.org/pdf/2603.24326 -
ByteDance Releases DeerFlow 2.0 Open-Source SuperAgent on GitHub
By
–
ByteDance dropped an open-source SuperAgent — and it hit #1 on GitHub Trending. DeerFlow 2.0 can: Deep web research with cited sources Generate full reports with charts, images & video Run Python & bash in a secure sandbox Create slide decks & UI components
-
Mistral Launches Voxtral Transcribe 2: Fast, Cheap, Open-Source
By
–
Mistral just upgraded Voxtral – and it's fast, cheap, and open. Voxtral Transcribe 2 comes in two flavors: • Mini – batch transcription, speaker diarization, word-level timestamps, 13 languages • Realtime – sub-200ms latency, open-source (Apache 2.0) Priced at