DEV Community

Minh Phuong Nguyen profile picture

Minh Phuong Nguyen

404 bio not found

Joined Joined on 
Why Developer Tools in 2026 Need to be 100% Client-Side

Why Developer Tools in 2026 Need to be 100% Client-Side

Comments
1 min read
Parsing DeepSeek's <think> Tags: A Guide to CoT Extraction

Parsing DeepSeek's <think> Tags: A Guide to CoT Extraction

Comments
1 min read
Is Your AI Agent Secure? How to Test for Prompt Injections in 2026

Is Your AI Agent Secure? How to Test for Prompt Injections in 2026

Comments
1 min read
Stop Overpaying for LLM APIs: A Token Cost Calculator for 2026

Stop Overpaying for LLM APIs: A Token Cost Calculator for 2026

Comments
1 min read
Stop Writing Boilerplate: A Visual Generator for MCP Server Schemas

Stop Writing Boilerplate: A Visual Generator for MCP Server Schemas

Comments
1 min read
Will It Fit? How to Calculate VRAM for Local LLMs (GGUF, EXL2) in 2026

Will It Fit? How to Calculate VRAM for Local LLMs (GGUF, EXL2) in 2026

Comments
1 min read
Mastering RAG: Why Your Text Chunking Strategy is Ruining Your AI App

Mastering RAG: Why Your Text Chunking Strategy is Ruining Your AI App

Comments
1 min read
Stop Writing Bad System Prompts

Stop Writing Bad System Prompts

Comments
1 min read
Offline API Workflows: Converting OpenAPI to Postman Without the Cloud

Offline API Workflows: Converting OpenAPI to Postman Without the Cloud

Comments
1 min read
Visualizing Multi-Agent Swarms: A Guide to Handoff Architecture

Visualizing Multi-Agent Swarms: A Guide to Handoff Architecture

1
Comments
1 min read
Will It Run in the Browser? Estimating WebGPU VRAM for LLMs

Will It Run in the Browser? Estimating WebGPU VRAM for LLMs

1
Comments
1 min read
Running LLMs in the Browser: A WebGPU & WebLLM Guide

Running LLMs in the Browser: A WebGPU & WebLLM Guide

1
Comments
1 min read
Stop Guessing Your RAG Chunk Size: A Visual Guide

Stop Guessing Your RAG Chunk Size: A Visual Guide

2
Comments
1 min read
Why Agentic Memory is the Missing Piece in Local AI

Why Agentic Memory is the Missing Piece in Local AI

1
Comments
2 min read
Building an MCP Inspector: Why Model Context Protocol is the Future

Building an MCP Inspector: Why Model Context Protocol is the Future

2
Comments
1 min read
Speculative Decoding in Practice: 3x Token Generation Speedup on Consumer GPUs (2026)

Speculative Decoding in Practice: 3x Token Generation Speedup on Consumer GPUs (2026)

2
Comments 2
2 min read
The 128k Context Illusion: How to Test 'Lost in the Middle' in Local LLMs

The 128k Context Illusion: How to Test 'Lost in the Middle' in Local LLMs

1
Comments 1
2 min read
How to Size Local LLMs: VRAM, KV Cache, and Hardware Architecture in 2026

How to Size Local LLMs: VRAM, KV Cache, and Hardware Architecture in 2026

Comments
3 min read
The Inference Paradox: Why Agentic Workflows Are 4x More Expensive Than You Think

The Inference Paradox: Why Agentic Workflows Are 4x More Expensive Than You Think

Comments 1
3 min read
Why I Built a 100% Client-Side Suite of 52+ Developer & AI Utilities

Why I Built a 100% Client-Side Suite of 52+ Developer & AI Utilities

Comments
2 min read
loading...