Agentic AI: On Evaluations | Towards Data Science
mostly a It’s not the most exciting topic, but more and more companies are paying attention. So it’s worth digging ...
Read more
Generating Structured Outputs from LLMs
interface for interacting with LLMs is through the classic chat UI found in ChatGPT, Gemini, or DeepSeek. The interface is ...
Read more
How Do Grayscale Images Affect Visual Anomaly Detection?
Introduction: Why grayscale images might affect anomaly detection. Anomaly detection, grayscale images: Quick recap on the two main subjects discussed ...
Read more
How I Fine-Tuned Granite-Vision 2B to Beat a 90B Model — Insights and Lessons Learned
or vision-language models is a powerful technique that unlocks their potential on specialized tasks. However, despite their effectiveness, these approaches ...
Read more
Exploratory Data Analysis: Gamma Spectroscopy in Python (Part 2)
part, I did an exploratory data analysis of the gamma spectroscopy data. We were able to see that using a ...
Read more
The Age of Self-Evolving AI Is Here
1. Introduction In one of my previous articles, we explored Google’s Titans (Behrouz et al., 2024)1 and how TTT (Test-Time ...
Read more
Your 1M+ Context Window LLM Is Less Powerful Than You Think
are now able to handle vast inputs — their context windows range between 200K (Claude) and 2M tokens (Gemini 1.5 Pro). That’s ...
Read more
How to Overlay a Heatmap on a Real Map with Python
need a simple, engaging, and scalable method for presenting geospatial data, they often turn to a heatmap. This 2D visualization ...
Read more
What Can the History of Data Tell Us About the Future of AI?
“Data is the fossil fuel of AI.” – Ilya Sutskever, co-founder and former chief scientist at OpenAI “The best prophet ...
Read more
Reducing Time to Value for Data Science Projects: Part 3
Parts 1 and 2 of this series focussed on the technical aspect of improving the experimentation process. This started with ...
Read more
