My first post
Welcome to my blog
Hello, everyone! My name is Gerard Boxó and I am excited to welcome you to my personal blog. Here, I plan to share my experiments, insights in the growing field of mechanistic interpretability.
About Me
I am a 20-year-old student pursuing my degree in Statistics at the University of Barcelona (UB). Here on this blog, I intend to share my journey through the fascinating landscapes of AI safety.
What is AI Explainability?
AI interpretability, in the simplest terms, is about making AI transparent, about shedding light on the ‘black box’. It’s the discipline of decoding how AI models, especially complex ones, make decisions from it’s more fundamental components. The objective? To ensure the fair, accountable, and safe use of AI in our society.
What’s on the Horizon?
The post will fall under the following cateegories:
-
Understanding AI Explainability: We’ll start from the basics and understand what AI Explainability is, why it’s important, and the key concepts involved.
-
Case Studies: I’ll share my experiments with different AI models, and their respectives modes of failure allways oriented to gain insight on their inner workin.
-
Tools and Techniques: We’ll explore various tools and techniques that aid in interpreting AI models.
-
Latest Research: Together, we will stay up-to-date with the latest research and developments in the field of AI Explainability.
-
Thoughts and Opinions: I’ll also share my thoughts and opinions on relevant topics.
#AI #ExplainableAI #MachineLearning #Blog