Jay Sensei👾
@hckinz
AI/ML, Cybersecurity, IR, AI art. Follow for Tech insights, learning, and unexpected blend of humor/culture. CPP| ViduAI 🧑🏻💻⚡🇮🇳🇯🇵
Google just released firebase.studio🙌 it's like lovable+cursor+replit+bolt+windsurf all in one @testingcatalog
Fuck ML tutorials. This is a collection of 300 ML system design case studies in real world, from Stripe, Spotify, Netflix, Meta, etc. Perfect for interviews and to learn how it’s done in the battlefield. Wish there was a similar thing for agents!
I have been fine-tuning LLMs for more that 2 years now! Here are the top 5 LLM fine-tuning techniques, explained with visuals:
for those struggling with deep learning math I resurface this tutorial I made last year in 27min I show my process by working through QHAdam optimizer which is this alphabet soup of letters
what are large language models actually doing? i read the 2025 textbook "Foundations of Large Language Models" by tong xiao and jingbo zhu and for the first time, i truly understood how they work. here’s everything you need to know about llms in 3 minutes↓
What is context engineering❓ And why is everyone talking about it...👇 Context engineering is rapidly becoming a crucial skill for AI engineers. It's no longer just about clever prompting; it's about the systematic orchestration of context. 🔷 The Problem: Most AI agents…
It looks like Nietzsche was wrong and Plato was right High powered Ai models are begin to converge on a “hidden realm” of ideals This is very hard for the layman to follow, but think of it this way: If I ask you to look at a tree, and then ask you to imagine a tree - your…
🚨 NEW LABS EXPERIMENT 🚨 Introducing Opal, our new way to help you build and share AI mini-apps by linking together prompts, models, and tools— all while using simple, natural language (without a single line of code 🤯) Now available in US-only public beta! Learn more ⬇️…
BREAKING 🚨: Google AI Labs released Opal experiment where users can "build and share AI mini-apps by linking together prompts, models, and tools". No-code AI workflows! 🤖 * US only for now
🚨 NEW LABS EXPERIMENT 🚨 Introducing Opal, our new way to help you build and share AI mini-apps by linking together prompts, models, and tools— all while using simple, natural language (without a single line of code 🤯) Now available in US-only public beta! Learn more ⬇️…
Microsoft released GitHub Spark in public preview for Copilot Pro+ subscribers. "Build and ship full-stack intelligent apps using natural language with access to the full power of the GitHub platform, no setup, no configuration, and no headaches."
I love playing with Spark myself, but even more, I’ve loved seeing what you're building. github.blog/changelog/2025…
Officially, creativity has no limits🧩 6,000 credits. 8 concurrent generations. Built for creators who move fast and think big. Quote tweet this thread and get a chance to win 1 Yearly Creator Plan. Introducing the Higgsfield Creator Plan →
Transformer vs. Mixture of Experts in LLMs, clearly explained (with visuals):
4 stages of training LLMs from scratch, clearly explained (with visuals):
I really like @warpdotdev , it smooth your working flow with terminal and lot of other task with its agentic mode. I was having some issue with my existing wsl linux distro and needed a new reinstall with copying my existing file into the host system. With just one prompt, it did…
Discover the newest experimental hybrid AI API that enables you to efficiently use on-device models (within Chrome) and cloud-hosted models. 📲 Chapters: 0:00 - Intro 0:56 - Set up 1:26 - Application 3:45 - Testing the application 4:58 - Recap
Ready to get started in Firebase Studio? Here's a handy thread of backend templates.
What does it 𝗮𝗰𝘁𝘂𝗮𝗹𝗹𝘆 take to build a production-level AI-first app? Not another demo. Not a weekend hackathon project. A real app with real users solving real problems. We just launched Glowe (glowe.app), an AI-powered Korean skincare recommendation…