Now tracking the origin of each parsed token to ensure it's organic and Fair Trade, and the location of tokens is shown in better error messages… Many other changes today, will likely make the next release tomorrow!
OPEN SOURCE
-
EmbeddingGemma: Multilingual On-Device Embedding Model in Browser
By
–
model carrot vibe coding another Google EmbeddingGemma app, a sota multilingual embedding model perfect for on-device use cases using transformers.js and onnx-community/embeddinggemma-300m-ONNX At only 308M params, the model can run 100% locally in your browser app:
-
Adam Optimizer: Fast.ai’s 2018 Breakthrough Research Discovery
By
–
Guess who was the 1st to point out that Adam can be used for pretty much everything? (Answer: it was @fastdotai back in 2018 — @GuggerSylvain
's first research project in fact!) https://
fast.ai/posts/2018-07-
02-adam-weight-decay.html
… -
Liquid AI Japan 350M Model Rivals GPT-4o Translation Performance
By
–
Liquid AI Japan cooked with this 350M param model on par with GPT-4o for English Japanese translation That's a really nice example of fine-tuning done right
-
Hugging Face Releases Impressive New Work and Blog Post
By
–
Hugging Face did it again! Insane work, beautiful blog post.
-
@aibreakfast — 2025-09-04
By
–
Chatterbox might be the biggest drop in AI audio yet:
— AI Breakfast (@AiBreakfast) 4 septembre 2025
-Open source
-Voice cloning with 5 seconds of audio
-Exceeds Elevenlabs in user satisfaction@resembleai does it again.
Amazing. pic.twitter.com/oclXTpd8YRChatterbox might be the biggest drop in AI audio yet: -Open source -Voice cloning with 5 seconds of audio
-Exceeds Elevenlabs in user satisfaction @resembleai does it again. Amazing. -
LangGraph: Essential Features for Production AI Agents
By
–
Building AI agents for production comes with unique challenges. In our latest blog, we share how we designed LangGraph to tackle them: Why heavy abstractions fail and what really matters for control & durability The 6 features every production agent needs in practice
-
MiniCPM-V 4.5 Achieves 77.0 Score Surpassing GPT-4o and Gemini
By
–
MiniCPM-V 4.5
— AK (@_akhaliq) 4 septembre 2025
achieves an average score of 77.0 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. With only 8B parameters, it surpasses widely used proprietary models like GPT-4o-latest, Gemini-2.0 Pro, and strong open-source models like Qwen2.5-VL 72B
powered… pic.twitter.com/H7s4zanvSKMiniCPM-V 4.5 achieves an average score of 77.0 on OpenCompass, a comprehensive evaluation of 8 popular benchmarks. With only 8B parameters, it surpasses widely used proprietary models like GPT-4o-latest, Gemini-2.0 Pro, and strong open-source models like Qwen2.5-VL 72B powered
