MACFE: MACFE: Meta-learning and Causality Based Feature Engineering | link.springer.com/chapter/10.100… Lang: Python ⭐️ 3 #MachineLearning github.com/Ivanrs297/MACFE

If you’re serious about mastering LLMs, agents, and AI systems start here. HuggingFace just released 9 elite-level AI courses for free ↓

Neural networks are stunningly powerful. This is old news: deep learning is state-of-the-art in many fields, like computer vision and natural language processing. (But not everywhere.) Why are neural networks so effective? I'll explain:

Prompting GPT-5 is different. In the examples below, optimized prompts: • Cut runtime by 1s • Dropped memory use 3,626 KB → 577 KB • Boosted code quality • Improved robustness (0.32→0.54) • Increased context grounding (0.80→0.95) We built a prompt migrator + optimizer

A new embedding model cuts vector DB costs by ~200x. It also outperforms OpenAI and Cohere models. Here's a complete breakdown (with visuals):

Google just dropped a new LLM! You can run it locally on just 0.5 GB RAM. Let's fine-tune this on our own data (100% locally):

[LG] A personal health large language model for sleep and fitness coaching J Khasentino, A Belyaeva, X Liu, Z Yang... [Google] (2025) nature.com/articles/s4159…

This is actually a really solid context engineering template. Kudos, Anthropic

ChatGPT system prompt is now 15k tokens

Seven tips for getting the best out of gpt-realtime:

AI Agents are amazing and continue to evolve, but let's face it: creating successful agents in production is not as easy as it might seem, and there are many ways for AI Agents to fail. Today we are sharing a new repository: github.com/vectara/awesom… The goal of this repository

AI agents that hack your app to find real security bugs

You're in a ML Engineer interview at Perplexity, and the interviewer asks: "Your RAG system is hallucinating in production. How do you diagnose what's broken - the retriever or the generator?" Here's how you can answer:

The recipe to make your AI app fail fast: make a giant do-it-all agent. Dump the planning, memory, user intent, and web search onto it. Monolith agents kill your scaling as the app grows. Break your agents down to subagents with specific tools and context.

I love this visual so much

Ivan Reyes (CINVESTAV GDL) whos has an oral talk and poster at the DEMI Workshop, entitled “Robust Federated Anomaly Detection Using Dual-Signal Autoencoders: Application to Kidney Stone Identification in Ureteroscopy”

Tracking and monitoring aren’t just for ML model training—they’re equally crucial in GenAI apps. 🚀 For both, #MLflow offers one of the best solutions to manage and scale experiments efficiently.

As usual, Anthropic just published another banger. This one is on context engineering. Great section on how it is different from prompt engineering. A must-read for AI devs.

How do you build effective AI Agents? This is a problem I think deeply about with other AI devs and students. Simplicity works well here. I think we can all learn a lot from how Claude Code works. The Claude Agent SDK Loop generalizes the approach to build all kinds of AI