I’m Alex Gude, a data scientist with a passion for plots and algorithms, but also cycling and photography. I got my start in the valley at Insight Data Science. In my previous life, I was a high energy particle physicist at CERN and a cosmologist at Lawrence Berkeley Labs.
I write about whatever catches my attention here on this site; mostly that means data science, machine learning, deep learning, and software development related topics. My writings on deep learning from my time at Lab41 can be found at Gab41 and rehosted on this page. If you’re interested in my thoughts in real time (as well as sneak peaks at what I’m writing), follow me at @alex_gude on Twitter and Mastodon, or at the handle @alexgude.com on BlueSky.
The code that I write lives on my Github page. Check it out! Bug reports and pull requests welcome!
Below you can find my most recent articles and projects; older ones can be found here:
Manually fixing messy data is tedious and slow. But thankfully, LLMs are pretty good are piecing together mangled text. Read on to find out how!
The RadWagon electric cargo bike was a savior during lockdown family rides, but frustrating maintenance and support issues disappoint. Read on for my in-depth review.
Return Actions, Not Scores
A poorly designed machine learning model API will leave you trapped. Properly hiding your implementation will make life much easier!
Word2Vec failed to solve SAT analogies, can modern language models do better? A small test of Anthropic's Claude LLM.
Large language models (LLMs) are incredibly valuable tools, but they're not for everything. Here's a simple rule to know when to use them and when to avoid them.