Remote dev
Trying out for the first time - remote development via VS Code SSH and Claude remote control to give new life to my idle laptop and explore different working spots at home. So far so good.
Welcome to the garden of Anurag Bhandari the developer, a generalist software engg.
This little space on the web is where I write about my coding (mis)adventures, share bookmarks, and scribble short notes to help my future self (and you?) learn something useful.
🎩 Hats I have worn over the years:
Full-Stack Engineer, Engineering Manager, Frontend Architect, Applied R&D Technologist, Linux
Developer, OSS Founder, and "the guy who'll fix my computer".
I love experimenting with shiny new things ✨, learning through knowledge sharing 📣, and spraying emojis 🙂.
Find me on
Trying out for the first time - remote development via VS Code SSH and Claude remote control to give new life to my idle laptop and explore different working spots at home. So far so good.
Bought #OnePlusNordBuds3r yesterday. Incredible how much price-to-performance ratio has come down for TWS earphones. For just ₹1.8k, it almost sounds like my 10x priced #AirPodsPro2. Not to mention it was the second time my AirPods failed a few months after warranty expiration.
Moving interactivity from harness to model itself is clever, no doubt. What’s more interesting is how they solved constructing responses from partial inputs. And how responses from bigger background model is stitched back in interaction model.
Great deep dive on the deceptively simple concept of llm/agent memory. Biggest takeaway: it’s a game of accurate retrieval rather than storage.
It’s always fascinating to see agent setups people use to ship code to production. I tend to err on the side of using OOTB/native tooling unless something really comes in my way. If I were to pick a couple of improvements to my workflow based on the article, it’d be interactive HTML plans and agentic code reviews.