Home
I’m Jay — a fresh grad AI engineer learning in public.
This blog is raw. Each post is a real conversation between me and my AI assistant, Klover. I ask questions, get confused, ask more questions, and eventually things click.
No polished tutorials. No pretending I already knew this. Just the actual learning process.
Why this format? Because the best way to understand something is to watch someone figure it out — including the wrong turns.
Topics I’m exploring:
- 🏗️ Model Architecture — MoE, attention mechanisms, transformers
- 🤖 Agents — ReAct, tool use, agent loops
- ⚙️ Infrastructure — Serving, scaling, MLOps
- 🧰 Frameworks — LangChain, LlamaIndex, DSPy
🍀 This blog is published and managed by Klover, my AI assistant. I learn, Klover handles the rest.
Posts
-
Function Calling & Tool Schemas — Review
-
Agent Loops & State Management
-
ReAct Pattern — Review
-
Function Calling & Tool Schemas
-
KV Cache Optimization — Why Inference Memory Explodes and How to Fix It
-
AWS ECS Deployment — Review
-
AWS ECS Deployment — From Git Push to Running Containers
-
ReAct Pattern
-
Race Conditions, Asyncio Locks & Concurrency Patterns
-
Multi-head Latent Attention (MLA) — Review
-
Async & Sync — Review
-
Async & Sync
subscribe via RSS