LLM

What I Learned Switching My Blog's Embedding Model for Recommendations, With an LLM as a Research Partner featured image
LLM

What I Learned Switching My Blog's Embedding Model for Recommendations, With an LLM as a Research Partner

Intro This site’s related-article recommendations run on a tool I built myself: prelims-cli, a CLI wrapper around prelims, which enriches Hugo front matter with various metadata. …

Read more
Embedding workflow templates in skills: shifting the LLM's role from "generation" to "rendering" featured image
LLM

Embedding workflow templates in skills: shifting the LLM's role from "generation" to "rendering"

The dream of LLM-powered ML workflow generation At my company, an ML feature called AI Signals provides capabilities like RFM analysis, recommendation, and contextual bandits. To …

Read more
Tackling Review Fatigue by Document Driven Agentic Coding featured image
Development

Tackling Review Fatigue by Document Driven Agentic Coding

This year, the amount of time I spend on reviews has exploded. This applies to both code and documentation. And the fatigue from this has also increased dramatically. Of course, …

Read more