@suraj.io - Suraj Deshmukh | सुरज देशमुख

14 Aug 2026 17:57 +0000

Recently I started using #herdr to run my agents in #Ghostty, wrote a post about how I reworked the shortcuts, so I don't have to use the prefix+ pattern (like #tmux): https://suraj.io/post/2026/ghostty-as-a-shell-for-herdr/ Landed on herdr+ghostty combo after having burnt with #cmux.

01 Jul 2026 00:00 +0000

AI agents are churning out massive PRs, accelerating our output but skyrocketing a new problem:Cognitive Debt. I wrote about the "Ironies of AI Coding," why we are losing our mental models, & how I built an AI-powered visual PR dashboard to get them back https://suraj.io/post/2026/ironies-of-ai-coding/

11 Jun 2026 23:44 +0000

Really cool tool to visualize what token/s really looks like at different speeds, starting from 0.05 tok/s to 2000 tok/s. After 800 tok/s you can't really tell the difference it all feels the same! https://mikeveerman.github.io/tokenspeed/?rate=30&mode=code

05 Jun 2026 00:34 +0000

This post highlights a critical issue with rapid, AI-driven development in team projects: long-term technical debt. If AI is helping you write code twice as fast, it's also doubling the amount of code you have to maintain. https://www.jamesshore.com/v2/blog/2026/you-need-ai-that-reduces-your-maintenance-costs

03 Jun 2026 23:45 +0000

NVIDIA Dynamo Snapshot: Fast Startup for Inference Workloads on Kubernetes https://developer.nvidia.com/blog/nvidia-dynamo-snapshot-fast-startup-for-inference-workloads-on-kubernetes/

03 Jun 2026 22:28 +0000

1/n We need to start talking about "KV Cache Engineering." The efficiency of any LLM serving system hinges on how it manages the KV cache—where to place it, how to discover it, and how long to keep it alive. Yet, most inference systems out there don't give clients the control they need.

22 May 2026 22:41 +0000

Using Claude Code: The unreasonable effectiveness of HTML How and why members of the Claude Code team use HTML instead of Markdown to produce richer, more readable, and easily shareable outputs. https://claude.com/blog/using-claude-code-the-unreasonable-effectiveness-of-html

13 May 2026 00:09 +0000

Is it ok to treat Claude generated code as if it was generated by another team you relied upon? What if you trust it too much because it worked in the past but then it bites you some day in the future? https://open.substack.com/pub/simonw/p/vibe-coding-and-agentic-engineering?r=ax4pb&utm_medium=ios

26 Apr 2026 02:38 +0000

Disaggregated Inference: 18 Months Later https://haoailab.com/blogs/distserve-retro/

25 Mar 2026 20:01 +0000

Official™️ Claude Code skill from Anthropic that creates Claude Code skills: https://github.com/anthropics/skills/tree/main/skills/skill-creator

17 Mar 2026 23:05 +0000

1/n I just spent time reading @simonwillison.net’s guide on agentic engineering patterns and it shifted how I think about coding with AI. The mindset isn’t “let the AI figure it out” — that’s vibe-coding™️.

17 Mar 2026 18:56 +0000

Living dangerously with Claude https://simonwillison.net/2025/Oct/22/living-dangerously-with-claude/

26 Feb 2026 19:10 +0000

Github has a recommendation on doing dotfiles: dotfiles.github.io https://dotfiles.github.io

23 Feb 2026 17:51 +0000

I just published a new guide on configuring #OpenClaw 🦀 to run with #Azure AI Foundry models. You control data control, so more privacy, talk to it from #Telegram or using the console! Check it out here: https://suraj.io/post/2026/openclaw-with-azure/

22 Feb 2026 20:00 +0000

Apple has a new native container CLI for macOS! Run Linux containers without Docker Desktop—with sub-second startup times. 🚀 My guide covers setup, resource limits, and fixing macOS firewall blocks: 🔗 https://suraj.io/post/2026/using-osx-containerization/ #macOS #Containers

17 Feb 2026 20:25 +0000

1/n 📚 Made something for fellow book nerds using Openclaw: A Goodreads skill that lets your AI agent search for books, pull up details & reviews, get personalized recommendations, and manage your reading lists — all through natural language. https://clawhub.ai/surajssd/goodreads

11 Feb 2026 00:28 +0000

Deploying #Kimi K2.5 on #Azure: A Complete Guide to Running MoonshotAI's Model https://suraj.io/post/2026/deploying-kimi-k2-on-azure/

08 Feb 2026 03:40 +0000

Running Pydantic’s Monty Rust sandboxed Python subset in WebAssembly https://simonwillison.net/2026/Feb/6/pydantic-monty/

03 Feb 2026 06:05 +0000

Thanks to @scott.hanselman.com for showing me Handy (handy.computer) — a free, open-source speech-to-text tool that runs locally on your machine. Push-to-talk, privacy-focused, and just works. Check it out! https://handy.computer

01 Feb 2026 23:56 +0000

Running Docker Commands on a Remote Machine via SSH https://suraj.io/post/2026/remote-machine-as-docker-runner/ #docker #ssh #remote #containers #cli #development #devops

01 Feb 2026 23:54 +0000

Using Claude Code with GitHub-Hosted Anthropic Models https://suraj.io/post/2026/use-claude-code-with-gh-models/ #claude #github-models #ai #litellm #anthropic

26 Nov 2025 14:26 +0000

Meta’s Kubernetes-based Portable AI Research Environment https://youtu.be/ts7bI51gRCo?si=TkhhTSBAHp6jmbU8

26 Nov 2025 01:30 +0000

Our talk (me & Yuhan Liu) on improving LLM serving efficienty is on YouTube now! https://youtu.be/2YCDvZokqnk?si=of1DG2k5dBIBN0I2 #vllm #kubernetes #kubecon

20 Nov 2025 00:25 +0000

Infinite scale: The architecture behind the Azure AI superfactory https://blogs.microsoft.com/blog/2025/11/12/infinite-scale-the-architecture-behind-the-azure-ai-superfactory/

20 Nov 2025 00:22 +0000

Gemini 3, Open AI kv cache and much more https://open.substack.com/pub/simonw/p/trying-out-gemini-3-pro-with-audio?r=ax4pb&utm_medium=ios

20 Nov 2025 00:16 +0000

Open AI gave some of the details from the user POV as to what kv cache features are available  https://platform.openai.com/docs/guides/prompt-caching  It is interesting to see that they cache for 10 min and if no request is found they remove hot caches from GPU

19 Nov 2025 04:10 +0000

From Wisconsin to Atlanta: Microsoft connects datacenters to build its first AI superfactory https://news.microsoft.com/source/features/ai/from-wisconsin-to-atlanta-microsoft-connects-datacenters-to-build-its-first-ai-superfactory/

15 Nov 2025 23:22 +0000

Satya Nadella – How Microsoft thinks about AGI https://youtu.be/8-boBsWcr5A?si=L15eJ4kpSqJSY4MJ

15 Nov 2025 20:53 +0000

How One Line of Code Freed 30,000 CPU Cores: Deep-Diving Fluent Bit at Petabyte Scale https://www.youtube.com/watch?v=pbOvWxuYPIU

11 Nov 2025 19:51 +0000

Come see us (me & Yuhan Liu) tomorrow for our talk. Specifically, Wednesday November 12, 2025 5:30pm - 6:00pm EST at Building B | Level 5 | Thomas Murphy Ballroom 1. More info: sched.co/27FcQ #kubecon #vllm https://sched.co/27FcQ