top of page
>szia.ai_
AI Explained


Engineering Intelligence from Autocomplete
Cover Photo: Made by Gemini Large Language Models (LLMs) don't think. They are simply predicting the next word (or "token") in a sequence. And yet, after a few days of using ChatGPT, Gemini, or Claude, you start treating them like thoughtful colleagues. You delegate tasks, ask for advice, and supervise their output as if they were intelligent entities (even letting them supervise parts of your daily workflow). How does a system designed to guess the next syllable end up solvi
Marton Antal Szel
Jan 2519 min read


Breaking Bot: Hacking & Defending LLM-based Applications
What happens when your AI chatbot becomes a genius saboteur? This post explores how attacks can slip past your safety guardrails - and the resilient architectures you need to ensure a breach doesn't turn into a catastrophe.
Marton Antal Szel
Dec 24, 202510 min read
bottom of page