Senior DevOps Architect and ML Engineerhttps://abhikhatri.com/https://abhikhatri.com/blog/what-code-llms-actually-lack/https://abhikhatri.com/blog/what-code-llms-actually-lack/I ran controlled experiments to figure out why code LLMs hallucinate cross-file references. The answer: they lack navigation, not comprehension. 14 tokens of symbol names gets 76% of the way. Full files get 92%. And you can inject the signal without any text at all.Wed, 15 Apr 2026 00:00:00 GMThttps://abhikhatri.com/blog/browser-video-editor-ffmpeg-wasm/https://abhikhatri.com/blog/browser-video-editor-ffmpeg-wasm/A browser-based video editor that runs entirely client-side using FFmpeg compiled to WebAssembly — no uploads, no servers, full privacy.Wed, 09 Jul 2025 00:00:00 GMThttps://abhikhatri.com/blog/the-unexpected-benefits-of-better-monitoring/https://abhikhatri.com/blog/the-unexpected-benefits-of-better-monitoring/Investing in Prometheus and Grafana did more than fix outages — it revealed performance bottlenecks, improved reliability, and changed how we think about building software.Wed, 21 May 2025 00:00:00 GMThttps://abhikhatri.com/blog/building-our-first-ai-powered-feature/https://abhikhatri.com/blog/building-our-first-ai-powered-feature/How we built and deployed our first AI feature — an auto-grading tool powered by a fine-tuned LLM — from model selection to production.Mon, 03 Mar 2025 00:00:00 GMThttps://abhikhatri.com/blog/why-we-moved-to-microservices/https://abhikhatri.com/blog/why-we-moved-to-microservices/How we broke apart our monolith into microservices on Kubernetes — faster deployments, better reliability, and 40% lower infrastructure costs.Wed, 15 Jan 2025 00:00:00 GMT