Search posts, tags, users, and pages
N I R A N J A N
Still learning. Already shipping. Blogging so you don't have to figure it out alone.
Part 3 of the series where I build an AI agent to learn how agents really work. This is the long one: the whole middle of the project, from writing the rules to measuring three different models. Here
Markdown supported · ⌘↵ to post
Salman Parvez | ML Systems
Self-taught full-stack engineer. Founder of ML Systems, a Rhode Island construction tech company. Shipped a React Native app to both stores
33% to 61% with the same model is a great example. Every gain came from the rules and checks around it, the way a crew gets better with the same people and a better process. The safety gate hitting 100% is the number I'd watch first.
Salman Parvez | ML Systems
Self-taught full-stack engineer. Founder of ML Systems, a Rhode Island construction tech company. Shipped a React Native app to both stores
33% to 61% with the same model is a great example. Every gain came from the rules and checks around it, the way a crew gets better with the same people and a better process. The safety gate hitting 100% is the number I'd watch first.