DEV Community

Jangwook Kim profile picture

Jangwook Kim

404 bio not found

Joined Joined on  Personal website https://effloow.com
ReFlect: Training-Free Error Recovery for Long-Horizon LLM Reasoning

ReFlect: Training-Free Error Recovery for Long-Horizon LLM Reasoning

Comments
4 min read
ZAYA1-8B: Zyphra's Efficient MoE Reasoning Model Guide

ZAYA1-8B: Zyphra's Efficient MoE Reasoning Model Guide

Comments
9 min read
Building a FastAPI + Claude API Streaming Production Backend — SSE, Retry, and Error Recovery Guide

Building a FastAPI + Claude API Streaming Production Backend — SSE, Retry, and Error Recovery Guide

Comments
7 min read
Snyk + Claude: AI Security for AI-Generated Code in 2026

Snyk + Claude: AI Security for AI-Generated Code in 2026

Comments
10 min read
ReaComp: Compile LLM Reasoning into Zero-Cost Symbolic Solvers

ReaComp: Compile LLM Reasoning into Zero-Cost Symbolic Solvers

Comments
10 min read
Google AI Studio Antigravity: Full-Stack Apps in One Prompt

Google AI Studio Antigravity: Full-Stack Apps in One Prompt

Comments
9 min read
Claude Code Masterclass #1 — Automating Workflows with Slash Commands, Hooks, and Subagents

Claude Code Masterclass #1 — Automating Workflows with Slash Commands, Hooks, and Subagents

Comments
7 min read
DRA-GRPO: Fixing Diversity Collapse in Reasoning Models

DRA-GRPO: Fixing Diversity Collapse in Reasoning Models

Comments
9 min read
Temporal for AI Agents: Durable Execution Guide 2026

Temporal for AI Agents: Durable Execution Guide 2026

Comments
10 min read
Adaptive KV-Cache Quantization: How 'Don't Waste Bits' Cuts On-Device LLM Latency by 17%

Adaptive KV-Cache Quantization: How 'Don't Waste Bits' Cuts On-Device LLM Latency by 17%

Comments
6 min read
Mastra AI 1.0: The TypeScript Agent Framework Developers Are Actually Shipping

Mastra AI 1.0: The TypeScript Agent Framework Developers Are Actually Shipping

Comments
6 min read
Qwen 3.6 Plus: 1M Context Coding Agent Developer Guide

Qwen 3.6 Plus: 1M Context Coding Agent Developer Guide

Comments
10 min read
Anthropic SDK vs OpenAI SDK: Developer Experience Compared — Type Safety, Error Handling, and Streaming Patterns

Anthropic SDK vs OpenAI SDK: Developer Experience Compared — Type Safety, Error Handling, and Streaming Patterns

Comments
7 min read
SpecKV: Adaptive Speculative Decoding with Dynamic Gamma

SpecKV: Adaptive Speculative Decoding with Dynamic Gamma

Comments
8 min read
DeepSeek-V3-0324: Open-Source Coding Model Developer Guide

DeepSeek-V3-0324: Open-Source Coding Model Developer Guide

Comments
9 min read
Kimi K2.6: The Open 1T-Param Model for Agentic Coding

Kimi K2.6: The Open 1T-Param Model for Agentic Coding

Comments
9 min read
Agent Test-Time Scaling Has a Ceiling: CMU Research 2026

Agent Test-Time Scaling Has a Ceiling: CMU Research 2026

Comments
9 min read
Cloudflare Dynamic Workers: V8 Sandbox for AI Agent Code

Cloudflare Dynamic Workers: V8 Sandbox for AI Agent Code

Comments
10 min read
GPT-Rosalind: OpenAI's Purpose-Built Drug Discovery Model

GPT-Rosalind: OpenAI's Purpose-Built Drug Discovery Model

Comments
6 min read
Claude Opus 4.7: High-Res Vision, Task Budgets, and Agentic Coding

Claude Opus 4.7: High-Res Vision, Task Budgets, and Agentic Coding

Comments
6 min read
VS Code Agent Mode in 2026: Companion App and MCP

VS Code Agent Mode in 2026: Companion App and MCP

Comments
8 min read
Setting Up AI Development with uv — Start a Claude SDK Project in Under 1 Second

Setting Up AI Development with uv — Start a Claude SDK Project in Under 1 Second

1
Comments
8 min read
MCP Code Execution: Build Token-Efficient AI Agents

MCP Code Execution: Build Token-Efficient AI Agents

Comments
10 min read
LangGraph + MCP: Build a Supervisor Multi-Agent System

LangGraph + MCP: Build a Supervisor Multi-Agent System

1
Comments
8 min read
Mistral Vibe Remote Agents: Medium 3.5 Developer Guide

Mistral Vibe Remote Agents: Medium 3.5 Developer Guide

Comments
9 min read
Gemini 2.5 Flash API Cost Optimization Guide — 99% Savings Confirmed by Real Experiments

Gemini 2.5 Flash API Cost Optimization Guide — 99% Savings Confirmed by Real Experiments

Comments
8 min read
Microsoft Agent Governance Toolkit: Developer Setup Guide

Microsoft Agent Governance Toolkit: Developer Setup Guide

Comments
9 min read
E2B Sandbox: Secure Code Execution for AI Agents

E2B Sandbox: Secure Code Execution for AI Agents

Comments
10 min read
Google TPU 8i: What the Inference Chip Split Means for Developers

Google TPU 8i: What the Inference Chip Split Means for Developers

Comments
5 min read
Build an AI Agent with MCP and TypeScript in 2026

Build an AI Agent with MCP and TypeScript in 2026

2
Comments
5 min read
Mistral Large 3: The 675B Open-Weight MoE Model Developer Guide

Mistral Large 3: The 675B Open-Weight MoE Model Developer Guide

Comments
5 min read
Qwen3-Coder: 27B Dense Model That Beats 397B MoE (2026)

Qwen3-Coder: 27B Dense Model That Beats 397B MoE (2026)

Comments
9 min read
Anthropic Files API Guide — Analyze Documents Without Re-uploading PDFs

Anthropic Files API Guide — Analyze Documents Without Re-uploading PDFs

Comments
7 min read
Claude Design and Claude Routines: Anthropic's New Agentic Products

Claude Design and Claude Routines: Anthropic's New Agentic Products

Comments
9 min read
RAGFlow: Self-Host a Deep-Document RAG Engine

RAGFlow: Self-Host a Deep-Document RAG Engine

Comments
10 min read
Claude Haiku 4.5: When to Use It Over Sonnet 4.6

Claude Haiku 4.5: When to Use It Over Sonnet 4.6

Comments
9 min read
Google ADK vs LangGraph 2026: I Installed Both and Compared Them Side by Side

Google ADK vs LangGraph 2026: I Installed Both and Compared Them Side by Side

Comments
6 min read
Microsoft Agent 365: AI Agent Governance for Developers

Microsoft Agent 365: AI Agent Governance for Developers

Comments
10 min read
Temporal for AI Agents: Durable Execution Guide 2026

Temporal for AI Agents: Durable Execution Guide 2026

Comments
9 min read
Intel OpenVINO 2026.0: Run LLMs on NPU for Free

Intel OpenVINO 2026.0: Run LLMs on NPU for Free

Comments
9 min read
POLARIS: Typed DAG Planning for Governed AI Agents

POLARIS: Typed DAG Planning for Governed AI Agents

Comments
10 min read
Cloudflare Moltworker: Self-Hosted AI Agents Without Hardware

Cloudflare Moltworker: Self-Hosted AI Agents Without Hardware

Comments
10 min read
Mercury 2: Inception's Diffusion LLM at 1,000 Tokens/s

Mercury 2: Inception's Diffusion LLM at 1,000 Tokens/s

Comments
9 min read
Langfuse v3 Self-Hosting Complete Guide — Building LLM Tracing on Your Own Infrastructure

Langfuse v3 Self-Hosting Complete Guide — Building LLM Tracing on Your Own Infrastructure

Comments
7 min read
Microsoft Agent Governance Toolkit: OWASP Agentic AI Top 10

Microsoft Agent Governance Toolkit: OWASP Agentic AI Top 10

Comments 1
10 min read
Cloudflare AI Gateway: Zero-Config LLM Proxy for Production

Cloudflare AI Gateway: Zero-Config LLM Proxy for Production

Comments
11 min read
Gemini 3.1 Flash TTS: Production API Guide for Developers

Gemini 3.1 Flash TTS: Production API Guide for Developers

Comments
8 min read
Why Anthropic Cut Off OpenClaw — The Claude Subscription Policy Shift and What It Costs You

Why Anthropic Cut Off OpenClaw — The Claude Subscription Policy Shift and What It Costs You

Comments
8 min read
Xiaomi MiMo-V2.5-Pro: Open-Source 1T Coding Agent Guide 2026

Xiaomi MiMo-V2.5-Pro: Open-Source 1T Coding Agent Guide 2026

Comments
9 min read
Devstral 2: Run Mistral's Open Coding Agent Locally

Devstral 2: Run Mistral's Open Coding Agent Locally

Comments
9 min read
Gemma 4 26B vs 31B: Which Model to Run Locally

Gemma 4 26B vs 31B: Which Model to Run Locally

Comments
10 min read
Anthropic's April Double Release — How Opus 4.7 and Managed Agents Change Agent Development

Anthropic's April Double Release — How Opus 4.7 and Managed Agents Change Agent Development

Comments
7 min read
Token Optimization for Production LLMs: Cut Costs Effectively

Token Optimization for Production LLMs: Cut Costs Effectively

Comments
10 min read
Build an MCP Server with TypeScript: 2026 Tutorial

Build an MCP Server with TypeScript: 2026 Tutorial

3
Comments 1
9 min read
LLM Prompt Caching in Production: Cut API Costs 78% With Claude

LLM Prompt Caching in Production: Cut API Costs 78% With Claude

Comments
7 min read
Claude Streaming + Tool Use: Build Real-Time Agentic Pipelines

Claude Streaming + Tool Use: Build Real-Time Agentic Pipelines

Comments
6 min read
OpenAI o3 Pro API: Maximum Reasoning for Hard Tasks

OpenAI o3 Pro API: Maximum Reasoning for Hard Tasks

Comments
9 min read
How to Build a PR Auto-Review Pipeline with GitHub Actions + Claude Code CLI

How to Build a PR Auto-Review Pipeline with GitHub Actions + Claude Code CLI

Comments
8 min read
DSPy 3.x: Compile and Optimize LLM Pipelines Automatically

DSPy 3.x: Compile and Optimize LLM Pipelines Automatically

Comments
9 min read
smolagents + MCP Bridge: Connect Any Tool to Your Agent

smolagents + MCP Bridge: Connect Any Tool to Your Agent

1
Comments
10 min read
loading...