You made a cool ML project. but it is completely unrelated to anything that the Arize community here focuses on: AI Observability and Evaluation.
2.
Your article requires serious fixing up. You left notes to yourself like (This will be a simple, Medium-friendly image.) Your last sentence is: "What repo name and blog title should I finalize?" It seems like you just pasted in a chatbot conversation.
Great paper released from Anthropic that's very relevant to the Observability community. Very clever way to do hierarchical clustering on users' conversations with an LLM. This allows them to get breakdowns on how people actually use Claude and to identify misuse that got past initial safety guardrails.
I could see these techniques integrating in Arize/Phoenix very nicely - and I'm sure the team was already headed down this path.
There are a lot of great ideas in the paper. I personally love the mix of new- and old-school ML. They use LLMs and everyone's favorite K-Means clustering.
Full disclosure: I am not an employee of Arize, so I do not speak on their behalf. But as an experienced AI practitioner, my recommendation is that you seek a community geared toward starting in machine learning.
