SearchSubscribe

P.K. SHARMA

Cyber security intelligence, AI governance, practitioner analysis

Playground

How AI actually works, one step at a time.

Interactive explainers you can click through. Each one shows the mechanism honestly, then shows where it breaks, because the two are the same thing. No sign-up, nothing sent anywhere, everything runs in your browser.

Interactive explainerHow RAG works, and how it gets poisonedWatch retrieval-augmented generation run step by step, then poison a document and watch the same system turn against its user.Run it →
Interactive explainerHow a language model actually worksWatch a sentence become tokens, then numbers, then a guess. Five steps from text to prediction, with a temperature dial you can turn.Run it →
Interactive explainerWhat actually happens when you press enter in ChatGPTYour six-word question becomes thousands of tokens. Follow the whole pipeline, then fill the context window until your own instructions fall out.Run it →
Interactive explainerHow an AI agent decides to actWatch an agent plan, call tools and loop. Then poison one tool result, and take a permission away to watch the same attack achieve nothing.Run it →