Skip to main content

2 posts tagged with "Machine Learning"

The science of getting computers to act without being explicitly programmed.

View All Tags

AI Embeddings: The Secret Sauce of Modern AI

· 7 min read
Christopher Brox
Building AI Agents @ Google

Have you ever had that slightly eerie feeling that your phone is reading your mind?

You’re searching for a "cozy weekend getaway," and suddenly, your favorite app starts recommending cabins in the woods, wool blankets, and crackling fireplaces. It didn’t just match the word "cozy"—it understood the vibe.

Or maybe you’ve noticed how Spotify knows exactly which "moody indie folk" song to play next, even if you’ve never heard of the artist. It’s not just looking at the genre; it’s looking at something deeper.

TL;DR

Embeddings are the bridge between how humans think (concepts, feelings, relationships) and how computers think (numbers). They turn messy ideas into a "Meaning Map" that AI can navigate.

Embracing Deterministic Decision Making - The Critical Role of Intent Classification in Generative AI Chatbots

· 12 min read
Christopher Brox
Building AI Agents @ Google

As artificial intelligence (AI) continues to evolve, one area that remains crucial is intent classification. In the midst of the constant excitement about generative models like GPT-4 and their abilities to produce human-like text, one might wonder, do we still need intent classification? The answer is a resounding yes and is rooted in the deterministic nature of intent classification, a trait that generative AI models, no matter how advanced, cannot currently replicate.