José David Baena – Distributed Systems Engineer https://josedavidbaena.com Production notes and source-backed analysis on distributed systems, messaging infrastructure, open-source internals, and model engineering. en-us josedab@gmail.com (José David Baena) josedab@gmail.com (José David Baena) Wed, 02 Sep 2026 00:00:00 GMT https://josedavidbaena.com/blog/distilled-engineering/llm-compression-decision-matrix LLM Compression Decision Matrix: Let the Bottleneck Pick the Technique https://josedavidbaena.com/blog/distilled-engineering/llm-compression-decision-matrix Choose pruning, quantization, distillation, LoRA, or MoE from the production bottleneck, then re-gate the exported artifact on target hardware. Wed, 02 Sep 2026 00:00:00 GMT josedab@gmail.com (José David Baena) llmmodel-compressionquantizationpruningdistillationloramixture-of-experts https://josedavidbaena.com/blog/distilled-engineering/model-distillation-antipatterns Model Distillation Breaks in the Same Ten Places Every Time https://josedavidbaena.com/blog/distilled-engineering/model-distillation-antipatterns A field guide to ten recurring distillation failures across data, evaluation, compression, serving, safety, and release governance. Wed, 26 Aug 2026 00:00:00 GMT josedab@gmail.com (José David Baena) model-distillationllmai-safetymlopsquantizationai-engineering https://josedavidbaena.com/blog/distilled-engineering/synthetic-data-factory A Synthetic Data Factory Needs Four Gates Before It Needs More Prompts https://josedavidbaena.com/blog/distilled-engineering/synthetic-data-factory Build a synthetic-data factory with curriculum allocation, schema checks, deduplication, decontamination, quarantine, and versioned release manifests. Wed, 19 Aug 2026 00:00:00 GMT josedab@gmail.com (José David Baena) synthetic-datamodel-distillationllmdata-qualitypythonai-engineering https://josedavidbaena.com/blog/distilled-engineering/dark-knowledge-soft-targets Dark Knowledge: What a Teacher's Wrong Answers Are Actually Worth https://josedavidbaena.com/blog/distilled-engineering/dark-knowledge-soft-targets Learn what soft targets preserve beyond hard labels, how temperature and KL direction change the signal, and when top-k logit storage loses too much. Wed, 12 Aug 2026 00:00:00 GMT josedab@gmail.com (José David Baena) model-distillationknowledge-distillationllmmachine-learningai-engineering https://josedavidbaena.com/blog/distilled-engineering/why-small-models-win-enterprise-ai Why Small Models Win the Enterprise AI Cost Argument https://josedavidbaena.com/blog/distilled-engineering/why-small-models-win-enterprise-ai Use a measurable service envelope and break-even model to decide when a distilled student beats a frontier API — and when it does not. Wed, 05 Aug 2026 00:00:00 GMT josedab@gmail.com (José David Baena) model-distillationllmenterprise-aicost-optimizationai-engineering https://josedavidbaena.com/blog/frontier-model-engineering Frontier Model Engineering: From Model Card to Production https://josedavidbaena.com/blog/frontier-model-engineering A four-workshop path from release forensics to durable agents, context storage, and topology-aware multi-GPU inference. Fri, 03 Jul 2026 00:00:00 GMT josedab@gmail.com (José David Baena) llmai-engineeringmodel-auditdistributed-inference https://josedavidbaena.com/blog/nanochat/building-chatgpt-for-100-dollars Build Your Own ChatGPT for $100 https://josedavidbaena.com/blog/nanochat/building-chatgpt-for-100-dollars Train a complete ChatGPT-like system from scratch for $100: tokenizer, pretraining, SFT, RL, deployment—the full LLM pipeline for the price of dinner. Tue, 14 Oct 2025 00:00:00 GMT josedab@gmail.com (José David Baena) machine-learningaitutorialllmdeep-learningpytorch https://josedavidbaena.com/blog/tiny-language-models/tiny-llm-architecture-comparison Tiny LLM Architecture Comparison: TinyLlama vs Phi-2 vs Gemma vs MobileLLM https://josedavidbaena.com/blog/tiny-language-models/tiny-llm-architecture-comparison Seven tiny models, one decision. Phi-2 wins on reasoning (56.7% MMLU). MobileLLM on speed (120 tok/s). Qwen on multilingual. Match constraints to model. Sat, 20 Sep 2025 00:00:00 GMT josedab@gmail.com (José David Baena) machine-learningllmarchitecturebenchmarkscomparison