I finally set up my homelab to be agentic-native. Custom MCP server, zero SSH, scoped access only. It's a different way to think about managing infrastructure with AI. Full write-up: https://t.co/6qmVQ9ClFb
I've been selected as an ambassador for the Linux Foundation's Agentic AI Foundation! I'll be sharing demos, blogs, and projects to highlight how the AAIF is paving the way for an open and save agentic world @AgenticAIFdn
@svpino I used to use Yabai to replicate an i3 experience, but I moved to AeroSpace and it removes all animations and is much quicker.
https://t.co/MQkYFHbYHV
Understanding the shortcomings of large language models (LLMs) requires understanding the shortcomings of the underlying evaluation metrics.
Evaluating Large Language Models III:
After covering perplexity and BLEU. Let's now discuss ROUGE.
1/8
All Python 🐍 developers should know about this module.
The module `collections` will make you 10x more productive*! 🚀
What is your favourite `collections` tool?
Let me show you some of its goodies in this thread. 👇
(*Actual numbers may vary. 🤡)
Deep Learning and Computational Physics (Lecture Notes)
Great notes on the connections between deep learning and computational physics. Lots of maths for those who like to dive deep.
https://t.co/N5KJlLL5TB
Two years ago I fell down the AI rabbit hole.
Since then, I tried to get (and stay) up to speed in AI — consuming all relevant papers, podcasts, blogs, etc... I could find.
Today, I'm sharing a first pass of my reading list. Hopefully it's helpful!
https://t.co/hEStAjI1vV
The way Python deals with variables is different from some other languages. You may even have heard some say they're not technically variables
Let's visualise what's happening when you create a name in Python and assign data to it with The Box and Label analogy
/1
You should always work on improving your model evaluation skills.
Model evaluation is the worst taught skill in machine learning, and I believe the best way of improving is through practice.
But, this paper from @rasbt is by far my favorite single written resource:
I'm proud to announce that I completed graduate school in computer science and data science from @coschoolofmines and will be working at @amazon as a machine learning engineer. I'm excited to work on some amazing problems with even more amazing people!