Visualizing and navigating branched conversations with LLMs and embeddings
I wrote about Conversation Branching on my main blog and I've been prototyping an LLM chat app called Delta that has first-class conversation branching. LLM conversations typically follow a linear path, making it unintuitive to explore alternative directions or recover from miscommunications. This...
About 6 months ago, I experimented with running a few different multi-modal (vision) language models on my Macbook. At the time, the results weren't so great.
Writing React/Tailwind with LLMs is effortless
If you've experimented with Claude Artifacts or v0.dev, maybe you've been delighted (as I have) that the language model can conjure a UI for an idea you describe. Most of my experience building software, especially professionally, comes from working on the "backend". Building frontend (read: user...
Deepseek V3 was recently released: a cheap, reliable, supposedly GPT-4 class model.
This year included a lot of writing and learning new things.
I've been building an Electron app called "Delta. Delta is a tool for knowledge exploration and ideation through the branching of conversations with language models. I have lots of ideas for how I want to make this idea useful and valuable, but today it looks like this.
I'm aiming to setup a space for more interactive UX experiments. My current Hugo blog has held up well with my scale of content but doesn't play nicely with modern Javascript frameworks, where most of the open source energy is currently invested.
In this notebook, we'll use the MovieLens 10M dataset and collaborative filtering to create a movie recommendation model. We'll use the data from movies.dat and ratings.dat to create embeddings that will help us predict ratings for movies I haven't watched yet.
I've started posting more on Bluesky and I noticed that articles from my site didn't have social image previews 😔
I explored how embeddings cluster by visualizing LLM-generated words across different categories. The visualizations helped build intuition about how these embeddings relate to each other in vector space. Most of the code was generated using Sonnet.