I work on applied AI projects and spend my spare time tinkering with models for fun. I write longer tweets at https://t.co/02byZNKMa8
Jan 5, 2025 • 7 tweets • 3 min read
Ever struggled to understand how users use your product?
I just built an open source implementation of Anthropic's internal clustering algorithm - CLIO.
With Gemini Flash, you can generate human readable labels which are clustered and grouped together to spot usage patterns.
Read more to find out how it works
We first generate summaries that redact PII of user conversations.
These are then embedded and clustered using a K-Means algorithm
Dec 30, 2024 • 9 tweets • 4 min read
I spent the weekend playing around with @v0 and generated almost 80% of this entire UI just by prompting from scratch
Here's a quick thread of 3 things I took away from how to prompt v0 better
1. Use @v0 to quickly generate and evaluate ideas for your UI.
For instance, when it came to the dashboard I wanted to create, I got it to create the following mock-ups to see what fit the best with what I had in mind.
At this point, you want to be thinking about
1. Color Schemes 2. Rough composition of UI 3. Animations you might want to use
Sep 14, 2024 • 7 tweets • 2 min read
1/ If you're building a RAG application, these problems probably sound familiar:
1. Irrelevant search results 2. Insufficient Data to create a database index 3. Multiple data sources that are out of sync 4. Untested LLM agents
How do these problems manifest?
2/ If you're just using embeddings for search, you're going to get items that belong to the wrong period or category without good metadata filters
