Skill exchange
A calm space to connect with others, share expertise, grow and build together — learn in real sessions, without noise or guesswork.
Welcome
Sign in with your email or Google.
New to Jiva? Create an account
By continuing you agree to trust-focused sessions, fair play, and our Terms & Conditions.
Stop struggling with Python constructors! This post breaks down __init__, self, default vs parameterized constructors, inheritance with super(), and common mistakes—with crystal-clear examples for absolute clarity.
Unlock the power of Object-Oriented Programming in Java with clear, practical lessons. Learn classes, inheritance, polymorphism, abstraction, and encapsulation through real-world examples and hands-on coding exercises.
I want to learn how APIs act as digital messengers between applications. I am exploring how apps send structured requests to servers, process data, and return responses seamlessly to better understand software integration and modern web architecture
Ever wonder how Claude reads your Google Drive or books a call? That’s the Model Context Protocol (MCP) — a trending open standard connecting AI models to external tools and data. Think of it as a “USB-C for AI”: instead of custom code for every app-model pairing, MCP gives one universal interface. A server exposes tools (like “search files” or “create event”); any MCP-compatible model can plug in and use them instantly. Why it matters: it turns static chatbots into agents that actually act — searching, scheduling, coding — without hardcoded integrations for each service.
Moonshot AI just dropped Kimi K3 — an open-weight model with 2.8 trillion parameters, making it the world’s first open 3-trillion-parameter-class model. The twist? Only 104 billion of those parameters activate per token, thanks to a Mixture-of-Experts design routing through 16 of 896 experts. Add a 1-million-token context window and native vision, and you get a model built for long-horizon coding and reasoning — competitive with frontier closed models, but one anyone can self-host.
I’m looking for someone to teach me AI agents. I want to understand how agents think/plan, use tools, and finish multi-step tasks — and then build a small working agent with guidance. Prefer live teaching with examples and doubt-clearing, not just a video dump.