This is an awesome approach to using MCP servers. We need more people to pay attention to this. Basically, convert a MCP spec into code functions, and have the model write code to call the functions, instead of typical tool-caling. I’ve been doing this with Python for a long
SOFTWARE
-
Essential Resources for CSS, JavaScript, SVG Web Animations
By
–
If you are working in CSS, JS, SVG, Web based animations you might find this guy's articles to be very useful and interesting.
-
Models Available on Hugging Face with Multi-Framework Support
By
–
All the models are available on Hugging Face and compatible with Transformers, vLLM, llama.cpp, and ollama out of the box.
-
ChatGPT Pulse launches personalized daily AI-powered news feed
By
–
🚨 ChatGPT just went from waiting for your questions to starting the conversation for you.
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 26 septembre 2025
Introducing ChatGPT Pulse – a daily feed of personalized updates researched overnight and ready when you wake up.
Rolling out to Pro users on mobile today.
Here’s how it works 👇 pic.twitter.com/eFeb00RaddChatGPT just went from waiting for your questions to starting the conversation for you. Introducing ChatGPT Pulse – a daily feed of personalized updates researched overnight and ready when you wake up. Rolling out to Pro users on mobile today. Here’s how it works
-
RPG: Repository Planning Graph for Unified Codebase Generation
By
–
RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation Luo et al.: https://
arxiv.org/abs/2509.16198 #ArtificialIntelligence #DeepLearning #MachineLearning -
GGUF Quantization: 350M Model Uses Just 380MB
By
–
Really tiny. We released GGUF quants, so with 8-bit precision and 4k context the 350M will use ~380 MB and the 1.2B ~1.4 GB (to give you a rough estimate).
-
Logo Programming Experiment with Python Turtle Package
By
–
Interesting. I am experimenting logo programming using python turtle package.
