Eduardo Alvarez·May 115 Agentic Design Patterns Everyone Should KnowA soft introduction to basic design patterns that underpin many of today’s agentic systems
Eduardo Alvarez·Aug 13, 2025Evolutionary Pseudocode with AI in the LoopExploring how AI could be the Latest Nested Loop in Evolutionary BiologyA response icon11A response icon11
Eduardo Alvarez·May 3, 2025What are LLM Tokens Worth?An initial dive into how LLM tokens translate into the economic impact for humans and businessA response icon1A response icon1
InTDS ArchivebyEduardo Alvarez·Apr 19, 2024Meta Llama 3 Optimized CPU Inference with Hugging Face and PyTorchLearn how to reduce model latency when deploying Meta* Llama 3 on CPUsA response icon2A response icon2
Eduardo Alvarez·Apr 5, 2024Transforming Financial Services with RAG: Personalized Financial AdviceSynthesize the complex web of financial strategies, regulations, and trends with a personalized financial advice RAG-based chatbot
Eduardo Alvarez·Apr 3, 2024Transforming Manufacturing with RAG: Delivering NextGen Equipment MaintenanceKeep operations online with actionable, relevant, and effective maintenance strategies with retrieval augmented generation
Eduardo Alvarez·Apr 2, 2024Transforming Retail with RAG: The Future of Personalized ShoppingDelivering dynamic, fresh, and timely recommendations to shoppers with retrieval augmented generation
InTDS ArchivebyEduardo Alvarez·Feb 29, 2024Improving LLM Inference Latency on CPUs with Model QuantizationDiscover how to significantly improve inference latency on CPUs using quantization techniques for mixed, int8, and int4 precisions.A response icon2A response icon2
InAWS TipbyEduardo Alvarez·Dec 20, 2023Distributed Fine-Tuning of Stable Diffusion with CPUs on AWSLearn how to use Hugging Face* Accelerate on Amazon Web Services (AWS)* to fine-tune Stable Diffusion
InTDS ArchivebyEduardo Alvarez·Dec 5, 2023Retrieval Augmented Generation (RAG) Inference Engines with LangChain on CPUsExploring scale, fidelity, and latency in AI applications with RAGA response icon1A response icon1
