Biblioteca de articulos
Articulos escritos por Guillermo J. Montenegro
Esta seccion muestra una parte central de mi experiencia: investigacion aplicada, criterio técnico y capacidad para explicar con claridad lo que experimento, construyo y aprendo.
No es una coleccion aislada de posts. Son articulos que escribi para dejar evidencia de mi forma de pensar, investigar y resolver problemas en IA, agentes, modelos y desarrollo de software.
No sci-fi, no philosophy: Capabilities and Limits of Neural Networks
Understanding neural networks as function approximators and their inherent limits.
Leer
Tools for LLMs step by step
Step‑by‑step guide on how system prompts define tool usage in large language models, with three difficulty levels covering basic calls, streaming inference, and token‑level fine‑tuning.
Leer
Determinism in LLMs
How to improve reproducibility in large language models.
Leer
The idea of AGI is broken, hi SROW
SROW(Same Result in its Own Way) is the real way to measure AI impact
Leer
Running LLMs Locally: Read This Before You Try at Home
A basic practical guide of concepts to understand open language models.
Leer
Sketching the New Coding Paradigm from the Roots
A brief sketch of the basic rules for development in the world of AI agents
Leer