OAuth Git credentials for service principals are now GA on GitHub and Azure DevOps! This means: No more PATs or manual rotation Tokens refresh automatically and expire after a few hours Repo-scoped access for tighter control Use OAuth to secure your Git integrations
TOOLS
-
Kimi K2 on Groq Enables Rapid Multi-Iteration App Development
By
–
Kimi K2 running blazing fast on @GroqInc inside @cline.
— Matt Shumer (@mattshumer_) 15 juillet 2025
It's only going to get faster from here.
Imagine full apps being built in minutes, and you as the developer get to choose from dozens of iterations and options at every step.
That's the world we're moving towards. pic.twitter.com/NlZBEESgyYKimi K2 running blazing fast on @GroqInc inside @cline
. It's only going to get faster from here. Imagine full apps being built in minutes, and you as the developer get to choose from dozens of iterations and options at every step. That's the world we're moving towards. -
Grok 4 Multimodal Voice Mode Thinks Aloud in Real Time
By
–
Grok 4 voit, parle, chante et pense à voix haute ! Si vous activez l'option : il observe, analyse et répond en temps réel. Le mode vocal de Grok 4 est assez bluffant… Il peut même divaguer comme s’il avait ses propres pensées. On peut littéralement lui montrer n’importe quoi… pic.twitter.com/CSaB3UsWjE
— VISION IA (@vision_ia) 15 juillet 2025Grok 4 voit, parle, chante et pense à voix haute ! Si vous activez l'option : il observe, analyse et répond en temps réel. Le mode vocal de Grok 4 est assez bluffant… Il peut même divaguer comme s’il avait ses propres pensées. On peut littéralement lui montrer n’importe quoi
-

Kontext LoRA for Old Damaged Photo Restoration Released
By
–
This kontext lora is now on Hugging Face https://
huggingface.co/fofr/kontext-o
ld-and-damaged-photo
… You get best results with guidance ~3.5 and a lora strength of ~1.4 (you're purposefully degrading the input) -

Free Automation Library Leak: 3000+ n8n Workflows and AI Tools
By
–
this might be the STUPIDEST thing i've ever done… leaking my ENTIRE automation library here's what you get: – 3,000+ n8n workflows including AI ad creative agents – AI UGC system that saves $247 per video (5-minute creation) – 100+ AI prompts that don't suck – Claude MCP AI agents for LinkedIn automation – AI prompts that write better than most humans – AI Viral Content OS (complete content empire) basically everything you need to automate your business Like + comment “VAULT” + repost (must be following so I can DM you) PS: only FREE for 24hrs before it goes into internal client systems
→ View original post on X — @thatroblennon, 2025-07-15 14:56 UTC
-
Mastering AI Tools: Complexity, Experience and Expertise Required
By
–
The CNC machine comparison works for me because it implies that they are tools that are complex, difficult to master and require a great deal of experience and knowledge to use effectively
-
Mistral launches Voxtral model with API and Hugging Face access
By
–
Try Voxtral with an API call: https://
console.mistral.ai, try it on Le Chat: http://
chat.mistral.ai, or download them on Hugging Face: https://
huggingface.co/mistralai. -

Voxtral outperforms Whisper and proprietary speech transcription models
By
–
Voxtral comprehensively outperforms Whisper large-v3, the current leading open-source Speech Transcription model, in speech transcription. It beats GPT-4o mini Transcribe and Gemini 2.5 Flash across all tasks, and achieves state-of-the-art results on English short-form and
-

World’s Best Open Speech Recognition Models Unveiled
By
–
Introducing the world's best (and open) speech recognition models!
-
Fine-Tuning Gemma 3n for Medical VQA: On-Device Clinical AI
By
–
📢Fine-Tuning Gemma 3n for Medical VQA
— Satya Mallick (@LearnOpenCV) 15 juillet 2025
The future of clinical AI is on-device, private, and specialized. We took Google's new Gemma 3n, a powerful but generalist VLM, and fine-tuned it to become a radiologist's assistant.
Our latest guide provides a deep dive into the process,… pic.twitter.com/r6AfxZEr7CFine-Tuning Gemma 3n for Medical VQA The future of clinical AI is on-device, private, and specialized. We took Google's new Gemma 3n, a powerful but generalist VLM, and fine-tuned it to become a radiologist's assistant. Our latest guide provides a deep dive into the process,
