I highly recommned this playlist on human behavior.

Architecture for multi-agent systems with observability and security Core 7 layers. ⚙️ - github.com/FareedKhan-dev…

And as a great man once said — the job’s not finished. On to what's next🚀

New art project. Train and inference GPT in 243 lines of pure, dependency-free Python. This is the *full* algorithmic content of what is needed. Everything else is just for efficiency. I cannot simplify this any further. gist.github.com/karpathy/8627f…

why is this free.. someone just curated 300+ real-world ML system case studies from companies like Netflix, Uber, and Airbnb.. it’s basically a $100k engineering degree in a single github repo. if you want to build at scale, you need to see this..

This GitHub repo isn’t a tutorial dump. It contains 28 production-ready AI projects you can actually use. Here’s what you’ll find inside: Machine Learning Projects → Airbnb price prediction → Flight fare calculator → Student performance tracker AI for Healthcare → Chest

RIP document extractors. Google just released LangExtract: Open-source. Free. Better than $100K enterprise tools. Here’s what it does: 🧵

The graduate-level course I co-teach each fall on deep learning at Massachusetts Institute of Technology (MIT) is now publicly and freely available through MIT's OpenCourseWare MIT OpenCourseWare !! Education for all ❤️❤️

Deep Learning with PyTorch step by step Total 3 volumes: - Vol.1 (Fundamentals) - Vol.2 (Computer Vision) - Vol.3 (Sequences and NLP) Official Repo: github.com/dvgodoy/PyTorc…

MCP vs RAG vs AI Agents

FAANG software engineer tells how they vibe code at FAANG

NVIDIA is giving free API keys You can even use models like Kimi-k2, minimax, etc

This free CUDA course is worth more than most CS degrees. 12 hours that separate library users from GPU engineers. I watched senior devs struggle with concepts taught in hour 3. What makes it different: No hand-waving. No "just use this library." You build an MLP trainer

🚨 I just read Google DeepMind’s new paper called "Intelligent AI Delegation." And it quietly exposes why 99% of AI agents will fail in the real world. Here’s the paper: Most “AI agents” today aren’t agents. They’re glorified task runners. You give them a goal. They break it

A graph-powered all-in-one RAG system! RAG-Anything is a graph-driven, all-in-one multimodal document processing RAG system built on LightRAG. It supports all content modalities within a single integrated framework. 100% open-source.