Dec 25, 2025 · 10 min read · How I identified a critical gap in one of Python's most popular LLM libraries and built two features to solve it. Introduction When I started exploring ways to contribute to open source, I wanted to find a project where I could make a real impact - ...
Join discussionDec 14, 2025 · 6 min read · You have probably encountered it already. A system that is brittle, poorly understood, and quietly dangerous. Then someone runs it through an AI assistant and suddenly there is a clean architecture diagram, a confident explanation, a tidy folder stru...
Join discussion
Dec 14, 2025 · 4 min read · Why does ChatGPT sound confident even when it is wrong?More importantly, how do we fix that? In this blog, you will build your first Retrieval-Augmented Generation (RAG) system in Python, step by step, with real code and no machine learning backgroun...
Join discussion
Dec 4, 2025 · 2 min read · También conocido como “Lavado de información en AI”, aka: “information laundering through AI”, Cómo una noticia falsa en un periódico acaba convertida en “verdad” por Grok, Claude y ChatGPT. Information laundering: cuando la IA convierte mierda en ...
Join discussion
Dec 2, 2025 · 4 min read · We’ve all been there. Faced with a technical question, you turn to a Large Language Model (LLM) for a quick, authoritative-sounding answer. But what happens when that answer is not just slightly off, but confidently and completely wrong? As someone w...
Join discussion
Nov 21, 2025 · 4 min read · How I Fought LLM Hallucinations in My RAG Chatbot When I built my RAG-based portfolio chatbot, I quickly discovered a harsh truth: giving an LLM access to a knowledge base doesn't automatically mean it'll stay truthful. It'll confidently invent detai...
Join discussionNov 20, 2025 · 4 min read · How I Fought LLM Hallucinations in My RAG Chatbot When I built my RAG-based portfolio chatbot, I quickly discovered a harsh truth: giving an LLM access to a knowledge base doesn't automatically mean it'll stay truthful. It'll confidently invent detai...
Join discussionOct 5, 2025 · 9 min read · How inference-time reasoning — Chain-of-Thought, ReAct, and Tree-of-Thoughts — is helping AI overcome its intuition and truly think. First thing First 🤔 Do LLMs Really Have “Intuition”? Strictly speaking — no, LLMs don’t have intuition or logic in t...
Join discussion
Aug 22, 2025 · 6 min read · Common Failure Cases and Quick Mitigations Retrieval-Augmented Generation (RAG) has revolutionized how Large Language Models (LLMs) access and utilize external knowledge, enabling them to generate more accurate, relevant, and up-to-date responses. Ho...
Join discussionJun 23, 2025 · 4 min read · You have misunderstood hallucination in AI. I'm going to explain what it is, what we get wrong, and why this is stopping you from getting the most value out of AI today. What Even Is a Hallucination This is the term we use when AI just makes somethin...
Join discussion