José Antonio Mancilla Chatú·Dec 15, 2025Beyond the Chatbot: A Postmortem on the Agentic AI FrontierOver the past few months, I’ve been immersed in the Agentic AI MOOC (https://agenticai-learning.org/f25), a deep dive into what many…
José Antonio Mancilla Chatú·Oct 2, 2025Poisoned Data, Broken Trust: Confronting AI’s Critical Alignment CrisisA recent study reveals AI can secretly learn bad behaviors from each other. If we don’t act now, the systems we rely on could be built on a…
José Antonio Mancilla Chatú·Sep 30, 2025From Generalist to Specialist: How I Turned GPT-4o into a Cybersecurity Assistant with Fine-TuningLarge Language Models (LLMs) like OpenAI’s GPT-4o are incredibly powerful. They’re like a Swiss Army knife of general knowledge — they can…
José Antonio Mancilla Chatú·May 28, 2025What are the fundamental inference-time techniques for enhancing large language model reasoning?Xinyun Chen of Google DeepMind’s introduction to the UC Berkeley Spring 2025 Advanced LLM Agents MOOC offered a deep dive into the…
José Antonio Mancilla Chatú·May 25, 2025The Dilemma of Security and Collaboration in Multi-Agent Systems: Striking a BalanceIn the heart of today’s technological revolution, multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a…
José Antonio Mancilla Chatú·Dec 13, 2024Hybrid Systems: A New Paradigm for Enhanced Planning in Large Language ModelsRecent research has highlighted significant limitations in Large Language Models (LLMs) when handling complex planning tasks. While LLMs…
José Antonio Mancilla Chatú·Jul 12, 2020Project: Arvato Bertelsmann Customer AnalysisThe goal of this project is to predict which individuals are most likely to convert into becoming customers for a mail-order sales company…
José Antonio Mancilla Chatú·Apr 11, 2020Can we guess Mexico Covid-19 confirme cases for the next 10 days?This is a novel process to predict Covid-19 confirmed cases in Mexico.