Aman Raj

Jul 17, 202620 min read

Where RAG Fails: Understanding the Limitations of Retrieval-Augmented Generation

Large language models can answer questions, write content, summarize information, and help with many other tasks. However, they have one important limitation: they do not automatically know everything

Secure Image Uploads from Expo to Amazon S3 Using Presigned URLs
Jul 14, 202611 min read
How to Run Open-Source AI Models Locally for Free on Mac and Windows
Jun 18, 202612 min read
Deploying Qwen3 235B on JarvisLabs with vLLM
Jun 17, 20267 min read
Stop Committing Your .env Files: The Global Gitignore Hack Every Developer Forgets
Apr 5, 20267 min read

the unsexy habits that actually get you hired
no shortcuts. no secrets. just patterns from people who did it.
Mar 14, 20264 min read
Cloudflare just made web crawling stupidly simple
a new /crawl endpoint for their Browser Rendering service
Mar 11, 20266 min read
OpenAI WebSocket Mode for Responses API: How to Use It and Why It's a Game-Changer for AI Agents (2026)
OpenAI just launched WebSocket mode for the Responses API — a persistent connection that cuts latency by up to 40% in agentic workflows. Learn how it works, how to integrate it in voice agents, and the top use cases you need to know.
Feb 24, 20267 min read
THE SILENT HEIST: HOW LLM DISTILLATION ATTACKS WORK AND WHY THEY ARE A THREAT TO AI'S FUTURE
DeepSeek, Moonshot AI, and MiniMax stole Claude's capabilities via distillation attacks. Learn how knowledge distillation works and how these attacks are carried out.
Feb 23, 20269 min read
The Only Fullstack Roadmap You Need for 2026: A No-BS Guide to Becoming an AI-Ready Developer
Skip the outdated tutorials. Learn the exact 8-phase blueprint to become a fullstack developer who ships AI-powered applications in 2026
Feb 2, 20266 min read
PostgreSQL as Queue, Cache, and Vector Database: 5 Ways to Simplify Your Stack
Why modern startups are ditching Redis, SQS, and specialized vector databases for one battle-tested workhorse
Feb 2, 202613 min read

Aman Raj

Latest articles

Where RAG Fails: Understanding the Limitations of Retrieval-Augmented Generation

Secure Image Uploads from Expo to Amazon S3 Using Presigned URLs

How to Run Open-Source AI Models Locally for Free on Mac and Windows

Deploying Qwen3 235B on JarvisLabs with vLLM

Stop Committing Your .env Files: The Global Gitignore Hack Every Developer Forgets

the unsexy habits that actually get you hired

Cloudflare just made web crawling stupidly simple

OpenAI WebSocket Mode for Responses API: How to Use It and Why It's a Game-Changer for AI Agents (2026)

THE SILENT HEIST: HOW LLM DISTILLATION ATTACKS WORK AND WHY THEY ARE A THREAT TO AI'S FUTURE

The Only Fullstack Roadmap You Need for 2026: A No-BS Guide to Becoming an AI-Ready Developer

PostgreSQL as Queue, Cache, and Vector Database: 5 Ways to Simplify Your Stack