Article library
Articles written by Guillermo J. Montenegro
This section shows a central part of my experience: applied research, technical judgment, and the ability to clearly explain what I experiment with, build, and learn.
This is not an isolated collection of posts. These are articles I wrote to show how I think, research, and solve problems in AI, agents, models, and software development.
No sci-fi, no philosophy: Capabilities and Limits of Neural Networks
Understanding neural networks as function approximators and their inherent limits.
Read
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.
Read
Determinism in LLMs
How to improve reproducibility in large language models.
Read
The idea of AGI is broken, hi SROW
SROW(Same Result in its Own Way) is the real way to measure AI impact
Read
Running LLMs Locally: Read This Before You Try at Home
A basic practical guide of concepts to understand open language models.
Read
Sketching the New Coding Paradigm from the Roots
A brief sketch of the basic rules for development in the world of AI agents
Read