Enigma

Note to future self :

Robotics with MATLAB Intro to robotics with a strong focus on learning by doing. You use simulations and animations to understand how robots work, while the math builds intuition step by step. The course shows how to write code for robot physics, control systems, and motion using MATLAB. Includes tutorials, example code, and a YouTube playlist for guided learning. 📍 pab47.github.io/robotics.html —— Weekly robotics and AI insights. Subscribe free: 22astronauts.com

1.Download Obsidian → create a new vault (folder) 2.Download Claude Desktop (Claude Code) 3.Point Claude to the path of your vault 4.Paste the prompt from the article > Just 4 steps and 10 minutes of your time The face I made when I realized I had been suffering all this time, not knowing such simple things

This 15-minute talk by the creator of Pydantic on how to correctly use MCPs will teach you more about making your AI tools actually work together than everything you've scrolled past this year. Bookmark this & watch, no matter what. Then read the guide below by @eng_khairallah1

This 2 hour Stanford lecture shows exactly how Stanford trains it's engineers to build AI systems. It's more practical than every Claude tutorial & prompting threads you've seen. Bookmark & give it 2 hours, no matter what. It'll be the most productive thing you do this weekend.

Programming drones with AI is a great way to learn about computer vision and automation. In this course, @beaucarnes helps you program a drone using Python and complete missions in a simulator. You’ll learn about 3D movement, computer vision, gesture control, and autonomous navigation. freecodecamp.org/news/master-ai…

30 Agents Every AI Engineer Must Build — Build production-ready agent systems using proven architectures and patterns: amzn.to/41ckg6z v/ @PacktDataML — What you will learn: 1️⃣Deploy production-ready agent systems that scale securely and reliably 2️⃣Use LangChain and LangGraph to build autonomous agents with modular architectures 3️⃣Implement agents with sophisticated memory, planning, and reasoning capabilities 4️⃣Seamlessly integrate tools, APIs, and external data into agent workflows 5️⃣Establish robust evaluation frameworks to measure and optimize agent performance 6️⃣Implement guardrails and explainability features to ensure ethical and safe deployment 7️⃣Build multi-agent systems for complex, collaborative task orchestration 8️⃣Apply specific agent architectures across healthcare, finance, and legal domains

Is context engineering the new RAG? (Hint: They are both about 𝗯𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝘁𝗵𝗲 𝗟𝗟𝗠’𝘀 𝗰𝗼𝗻𝘁𝗲𝘅𝘁) 𝗥𝗔𝗚 (𝟮𝟬𝟮𝟬-𝟮𝟬𝟮𝟯): One-shot retrieval • Fixed retrieval pipelie • Always retrieve context (whether you need it or not) • Retrieve exactly once (even if you need more info) 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 (𝟮𝟬𝟮𝟯-𝟮𝟬𝟮𝟰): Multi-hop retrieval through tool usage • Retrieval becomes a tool the agent can choose to use • Agent decides: Do I need to retrieve? Is this context even relevant? Do I need more? • Can route to different indexes 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝘀𝗲𝗮𝗿𝗰𝗵 𝗶𝗻 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴 (𝟮𝟬𝟮𝟱+): Combine multiple retrieval tools for context engineering • Context is scattered across different context sources (database, filesystem, web, memory) • Combine different context retrieval tools • Agent builds its own context Essentially, we’ve moved from ‘retrieve once’ to ‘the agent builds its own context’. Yesterday, I gave a workshop on this topic. Find the slides and code on this in my GitHub repo: github.com/iamleonie/work…

Our new Stanford class "CME 296: Diffusion & Large Vision Models" is now available on YouTube!

Roadmap to Become an Agentic AI Engineer in 2026 drive.google.com/file/d/1JkNUDO…

🚨 MIT proved you can delete 90% of a neural network without losing accuracy. Researchers found that inside every massive model, there is a "winning ticket”, a tiny subnetwork that does all the heavy lifting. They proved if you find it and reset it to its original state, it performs exactly like the giant version. But there was a catch that killed adoption instantly.. you had to train the massive model first to find the ticket. nobody wanted to train twice just to deploy once. it was a cool academic flex, but useless for production. The original 2018 paper was mind-blowing: But today, after 8 years… We finally have the silicon-level breakthrough we were waiting for: structured sparsity. Modern GPUs (NVIDIA Ampere+) don’t just “simulate” pruning anymore. They have native support for block sparsity (2:4 patterns) built directly into the hardware. It’s not theoretical, it’s silicon-level acceleration. The math is terrifyingly good: a 90% sparse network = 50% less memory bandwidth + 2× compute throughput. Real speed.. zero accuracy loss. Three things just made this production-ready in 2026: - pruning-aware training (you train sparse from day one) - native support in pytorch 2.0 and the apple neural engine - the realization that ai models are 90% redundant by design Evolution over-parameterizes everything. We’re finally learning how to prune. The era of bloated, inefficient models is officially over. The tooling finally caught up to the theory, and the winners are going to be the ones who stop paying for 90% of weights they don’t even need. The future of AI is smaller, faster, and smarter.

🚨BREAKING: Google just dropped Google skills. A new platform where anyone can learn ai, coding, and tech from scratch with certificates. Here is everything you need to know:

A full MIT course on visual autonomous navigation. If you work on robotics, drones, or self-driving systems, this one is worth bookmarking‼️ MIT’s Visual Navigation for Autonomous Vehicles course covers the full perception-to-control stack, not just isolated algorithms. What it focuses on: • 2D and 3D vision for navigation • Visual and visual-inertial odometry for state estimation • Place recognition and SLAM for localization and mapping • Trajectory optimization for motion planning • Learning-based perception in geometric settings All material is available publicly, including slides and notes. 📍vnav.mit.edu If you know other solid resources on vision-based autonomy, feel free to share them. —— Weekly robotics and AI insights. Subscribe free: 22astronauts.com

This is Algebrica. A mathematical knowledge base I’ve been building for 2.5 years. 215+ entries, carefully written and structured. 400k+ views over this time. Not much in absolute terms, but meaningful to me. No ads. No courses to sell. No gamification. No distractions. Just essential pages, aiming to explain mathematics as clearly as possible, for a university-level audience. Built simply for the pleasure of sharing knowledge. Content licensed under Creative Commons (BY-NC). Best experienced on desktop. If it helps even a few people understand something better, it’s worth it.

Every team at your company should be creating their own 'Team OS' in Claude Code on Github. Here's how: 1:45 - What is a Team OS 13:37 - Shared skills and commands 25:24 - Shared team automations 59:50 - The learning flywheel

In 2013, Nassim Taleb gave a 53-min Stanford masterclass on why chaos makes some businesses stronger. His ideas: - The coffee cup that survives 4 million hits - Why helicopter engineers ride their own machines - The country where nobody knows the president 12 lessons on risk:

The only roadmap you’ll ever need to become an Agentic AI Engineer in 2026 ✨ drive.google.com/file/d/1mQWpRq…

wanted to learn Arduino but had no hardware turns out you don't need it Velxio runs Arduino, ESP32, Raspberry Pi, and RISC-V code directly in your browser.... real emulation 48+ components. no install. no account. completely free velxio.dev the hardware excuse is gone

I was just explaining the dot product to my son today! It's used everywhere in games, often with unit vectors to determine how aligned they are. But if it’s never really clicked for you, this thread is full of visual examples.

STANFORD UNIVERSITY compressed the entire field of LLMs and transformers into free cheatsheets anyone can use today. It covers everything from self-attention to Flash Attention, LoRA, SFT, MoE, distillation, quantization, RAG, agents, and LLM-as-a-judge. 100% Free and Open Source

My friend Milla Jovovich and I spent months creating an AI memory system with Claude. It just posted a perfect score on the standard benchmark - beating every product in the space, free or paid. It's called MemPalace, and it works nothing like anything else out there. Instead of sending your data to a background agent in the cloud, it mines your conversations locally and organizes them into a palace - a structured architecture with wings, halls, and rooms that mirrors how human memory actually works. Here is what that gets you: → Your AI knows who you are before you type a single word - family, projects, preferences, loaded in ~120 tokens → Palace architecture organizes memories by domain and type - not a flat list of facts, a navigable structure → Semantic search across months of conversations finds the answer in position 1 or 2 → AAAK compression fits your entire life context into 120 tokens - 30x lossless compression any LLM reads natively → Contradiction detection catches wrong names, wrong pronouns, wrong ages before you ever see them The benchmarks: 100% recall on LongMemEval — first perfect score ever recorded. 500/500 questions. Every question type at 100%. 92.9% on ConvoMem — more than 2x Mem0's score. 100% on LoCoMo — every multi-hop reasoning category, including temporal inference which stumps most systems. No API key. No cloud. No subscription. One dependency. Runs on your machine. Your memories never leave. MIT License. 100% Open Source. github.com/milla-jovovich…