Pinnedprogrammerraja·Sep 21, 20252025 Voice AI Guide: How to Make Your Own Real-Time Voice Agent (Part-1)Over the past few months I’ve been building a fully open-source voice agent, exploring the stack end-to-end and learning a ton along the…A response icon4A response icon4
Pinnedprogrammerraja·Dec 15, 2024Generative AI: A Personal Deep Dive-My Notes and InsightsHey Everyone! As the world increasingly moves toward AI-driven solutions, I, as a full-stack developer, became intrigued by the potential…
programmerraja·Nov 5I Let AI Type the Code and Lost the MapI coded by hand for about three years. When a feature was done, I could close the file and still remember it. I knew which function ran…
programmerraja·Oct 29Sherlock Holmes: Why Prewarming a Voice Agent Didn’t Make the First Reply FasterThis is one case from the Sherlock Holmes series. Each write-up is a production problem me had to take apart. feel free to checkout other…A response icon1A response icon1
programmerraja·Sep 23How Jev Works: The Logit Trick Behind TypeSafe’s System One ModelFor the last few weeks my timeline has been nothing but Jev.
programmerraja·Sep 5How We Doubled Our Cache Hit Rate for Voice Agent When Pre-Warming Wasn’t EnoughA clean upward line, which is exactly what you would expect. Caching was working inside a conversation. Turn 2 reused turn 1, turn 3 reused…
programmerraja·May 17Interview Experience After 3 Years in a Company: Key LearningsI’ve been working as a full-stack developer at a startup for the past 3+ years. Recently, I decided to switch companies to explore new…
programmerraja·Mar 1Sherlock Holmes: The Case Of AI Brought Down Our ServersThere are two kinds of production incidents.
programmerraja·Feb 10Prompt Engineering From First Principles: The Mechanics They Don’t Teach You part-2In Part 1, we established a fundamental truth: LLMs are probability engines, not reasoning machines. They don’t “know” anything; they…