Long-form essays on generative AI, agent loops, inference engines, and backend systems. Published through Substack and open for discussion.
A deep dive into Time-To-First-Token (TTFT) pre-warming, invariant prompt prefix caching, turn delta compression, and Apple Silicon Metal GPU acceleration for autonomous AI agents.
To truly understand Large Language Model (LLM) inferencing at a deep technical level, we must look past the simple abstraction of “predicting the next word”.
If you’ve used Large Language Models to write code for longer than 10 minutes, you’ve likely run into the Context Wall.
If you've spent any significant time building with LLMs, you know the feeling.
The first thing people usually do while designing systems is jump directly into databases, microservices, Kubernetes, Redis, queues, and scaling.
Asynchronous Architecture
Andrej Karpathy just broke the internet with a new research method that is going to fundamentally change how we all use AI.
Not all improvements come from adding complexity -- sometimes it’s about removing it.
Stop the Thundering Herd! Explore Jitter, Probabilistic Re-computation, SWR, and Cache Warming to keep your high-traffic systems stable during Netflix-scale spikes.
Imagine you’re standing outside Apple store on the release of it’s new store.
In the middle of AI Revolution, it is for sure that any industry it touches, it promises great innovations but also introduces new challenges.
Imagine talking to a friend who forgets everything you’ve ever said.
The way money is transferred in India has fundamentally changed over the last decade.
🚀 Introducing PromptOS: Your AI Prompt Companion
As a developer, I have come across this term proxy many times when in a discussion with another fellow developer.
With the introduction of MCP Servers, it has changed the entire game of LLMs from just being able to give the response now to able to execute them with the help of tools.
Here are 10 lesser-known but insanely useful GitHub Actions you should be using.
Before HTML5, developers used frameset for SPA-like functionality, dividing the window into multiple frames, each with its own unique name.
Tired of thinking what comments to add for your git commit. This flow will help you.
Whenever it comes to creating a project or making a project, the most crucial part of it is to have an approach to it. Many a times, what developers do is that they directly start creating the project
Just a small introduction of myself