gayatri r·Apr 29How LLMs Actually Work: From 35B Parameters to Running in LM Studio & OllamaWhat is inside an LLM? (The conceptual building blocks) What is the architecture? (How those blocks are connected) How does a 35B parameter…
gayatri r·Apr 29What ‘35B Parameters’ Means in Qwen and Why It MattersIn the context of large language models (LLMs) like Qwen, "parameters" refer to the weights and biases that the model learns during its…
gayatri r·Apr 27Adversarial AttacksAn FSGM attack (Fast Gradient Sign Method attack) is a type of **adversarial attack** used against machine learning models, particularly…
gayatri r·Mar 19ML Model Bias & Hallucination Auditing MethodologyDomain: Artificial Intelligence Security & Governance Focus: Generative AI, Large Language Models (LLMs)
gayatri r·Jan 23Inside the OWASP Agentic AI Top 10: Exploitation and Architecture in Autonomous Systems1. Introduction: The Evolution from Chatbots to Autonomous Agents
gayatri r·Jan 143 Sneaky Ways People Are Tricking AI Resume Scanners (And How Well It Works)Introduction: The New Gatekeepers of Your Dream Job
gayatri r·Jan 3A Beginner’s Guide to the Model Context Protocol (MCP) and Its Security RisksIntroduction
