Writing

Lists

2026

Sep 8

Your Coding Agent Doesn't Have Memory. It Has a Really Good Notebook.

Everyone assumes coding agents remember your project with embeddings. They don't. Here's the actual mechanism: static files, capped indexes, and silent context rewrites.

CODING AGENTSAI CODING AGENT ARCHITECTURE
Sep 2

Same job, thirteen completely different architectures: how today's top coding agents actually differ

A source-code teardown of 13 coding agents finds their real differences aren't "plans, uses tools, reflects" but how they route models, compact context, and handle safety.

CODING AGENTSAI CODING AGENT ARCHITECTURE
Mar 1

Rate Limitting Explained: The Bouncer Your API Deserves

Rate limiting controls how many requests a user can make within a given time period. When the limit is exceeded, further requests are rejected until the window resets or capacity is replenished. In this post, we break down the 3 most common algorithms, their trade-offs, and how companies like GitHub, Stripe, and Cloudflare use them in production.

SYSTEM DESIGN
Feb 22

I Tested 4 RL Algorithms on 4 Environments and PPO Isn't Always King

From scratch implementations of REINFORCE, PPO, GRPO, and CPGD reveal surprising winners and losers across CartPole to MountainCar with a fixed budget, simpler often beats sophisticated.

MACHINE LEARNINGREINFORCEMENT LEARNING
Parth Thirwani
Parth Thirwani
Home
Resume
  • 📄Books1
  • 📌Quotes3
  • 💻Projects10
  • 📈Publications4
  • 📝Writing4