#machine learning
Here are my latest articles filed under machine learning. Showing page 1 of 1 (3 total articles).
Why 8-bit quantization can halve LLM size and how outlier weights spoil it
8-bit quantization can shrink a language model dramatically, but a single outlier weight can break everything. Here’s how to do it right.
Understanding Recursive Self-Improvement in AI and Its Practical Limits
Recursive self‑improvement is the idea that an AI can upgrade itself. I break down the concept, the mechanisms, and the practical hurdles you’ll hit.
Understanding How Transformers Capture Meaning in Language Models
Explore how transformers turn words into meaning, using attention and embeddings, in a clear, beginner‑friendly guide.
Need help building a website?
Send me a message and let's talk.