Snigdha Keshariya

Snigdha Keshariya

Snigdha Keshariya covers AI concepts and tools, from AI agents, RLHF, prompting, and model architectures to coding assistants and AI productivity tools.

What Are AI Agents? The Easiest Explanation

What Are AI Agents? The Easiest Explanation

An artificial intelligence (AI) agent does more than generate an answer. It works toward a goal, chooses steps, uses permitted tools, checks the result, and decides what to do next. I checked that definition against OpenAI and IBM’s agent documentation…

What is RLHF? How It Works in ChatGPT

What is RLHF? How It Works in ChatGPT

Reinforcement learning from human feedback (RLHF) turns human judgments about model responses into a training signal, and OpenAI documented it as part of the original ChatGPT training pipeline. People do not approve every answer you receive because their earlier demonstrations…

Mixture of Experts DeepSeek: How MoE Models Work

Mixture of Experts DeepSeek: How MoE Models Work

I checked the public DeepSeek-V3 technical report because it gives an inspectable Mixture of Experts (MoE) example: the model has 671 billion main-model parameters, but its active path uses 37 billion parameters for each token. DeepSeek can keep a large…

How to Use Black Box AI for Coding

How to Use Black Box AI for Coding

BLACKBOX AI gives you a browser app, a Visual Studio Code agent, a command-line interface (CLI), and an application programming interface (API), so this guide uses the current marketplace listing, official pricing, and a JavaScript acceptance test run with Node.js…