Tech Jupjup desk

AI

Hands-on notes on AI tools, models, and open-source projects filtered for real work.

What Is Vectorless RAG? Is PageIndex a Real RAG Alternative?
AIGuides

What Is Vectorless RAG? Is PageIndex a Real RAG Alternative?

A current guide to why PageIndex says it can search long documents without vector databases or chunking, and how to read its pricing, MCP surface, FinanceBench claims, and real limits.

Read
What Is PlayMCP? Kakao's MCP Hub and OpenClaw Integration Explained
AIGuides

What Is PlayMCP? Kakao's MCP Hub and OpenClaw Integration Explained

A current guide to what PlayMCP really is, how Kakao's toolbox and mcp-gateway work, and why the OpenClaw integration matters.

Read
How to Use NotebookLM in 2026: Free Limits, Upgrade Triggers, and Gemini Workflow
GuidesAI

How to Use NotebookLM in 2026: Free Limits, Upgrade Triggers, and Gemini Workflow

A practical NotebookLM guide covering free limits, Deep Research, Gemini Notebooks, file generation, privacy caveats, and when to upgrade.

Read
Recordly Review: A Free Screen Studio Alternative With Auto Zoom, GIF Export, and Korean UI
GuidesAI

Recordly Review: A Free Screen Studio Alternative With Auto Zoom, GIF Export, and Korean UI

A hands-on Recordly review covering auto zoom, captions, cursor polish, webcam controls, extension support, current bugs, and where it stands against Screen Studio and Loom.

Read
Andrej Karpathy's 4 AI Coding Warnings and the 100K-Star CLAUDE.md Repo
AIGuides

Andrej Karpathy's 4 AI Coding Warnings and the 100K-Star CLAUDE.md Repo

A deep dive into the four bad AI coding habits Karpathy warned about, the CLAUDE.md repo's four operating principles, what evidence supports them, and where the limits still are.

Read
LG EXAONE 4.5 and the Real State of Korean Local LLMs
AI

LG EXAONE 4.5 and the Real State of Korean Local LLMs

A practical overview of EXAONE 4.5, HyperCLOVA X SEED, Kanana 2, A.X 4.0, Mi:dm 2.0, and Solar Pro 3, focused on licensing, deployment, and real Korean-language capability.

Read
Oh My OpenAgent Review: A Multi-Agent Alternative to Claude Code (2026)
AIGuides

Oh My OpenAgent Review: A Multi-Agent Alternative to Claude Code (2026)

An honest one-month review of OpenCode + Oh My OpenAgent, covering ultrawork, agent roles, pricing, failure modes, and whether it is ready to replace Claude Code.

Read
Qwen 3.6 27B Review: A Local Coding Agent Tested on RTX 4090 and M4 Max (2026)
AIGuides

Qwen 3.6 27B Review: A Local Coding Agent Tested on RTX 4090 and M4 Max (2026)

A practical review of Qwen 3.6 27B and 35B-A3B for local coding work, covering benchmarks, VRAM, token speed, Apache 2.0 licensing, and Claude alternatives.

Read
AI Apps Are Built with Harnesses, Not Prompts
AIGuides

AI Apps Are Built with Harnesses, Not Prompts

A practical guide to harness engineering: context, tools, evals, observability, CI gates, and security for production AI apps.

Read
GPT-5.5 Review: Benchmarks, Pricing, Codex Impact, and Early Reactions (2026)
AI

GPT-5.5 Review: Benchmarks, Pricing, Codex Impact, and Early Reactions (2026)

What changed in GPT-5.5, where it leads on agent benchmarks, why pricing looks 2x higher, and how Codex users should think about upgrading as of April 2026.

Read
HOP HWP Desktop App Guide 2026: Open HWP and HWPX on Mac, Windows, and Linux for Free
GuidesAI

HOP HWP Desktop App Guide 2026: Open HWP and HWPX on Mac, Windows, and Linux for Free

A practical guide to HOP, the free desktop app for opening HWP and HWPX files without Hancom. Covers download links, installation, PDF export, and how it differs from RHWP.

Read
GLM 5.1 Review: Run Claude Code at 1/5 the Price with Open-Weight SOTA
AI

GLM 5.1 Review: Run Claude Code at 1/5 the Price with Open-Weight SOTA

How to run GLM 5.1 in Claude Code at one-fifth the cost, plus what Z.AI's official docs reveal about subscription-backed API access, Vision MCP, and GLM-Image.

Read
Kimi K2.6 Deep Dive: 88% Cheaper Claude Opus 4.7 Alternative?
AI

Kimi K2.6 Deep Dive: 88% Cheaper Claude Opus 4.7 Alternative?

Kimi K2.6 is an open-weight MoE model with SWE-Bench Pro 58.6, HLE 54.0, 300-agent swarms, 256K context, and API pricing about 88% below Claude Opus 4.7.

Read
Cut Claude Code Tokens 71x with Graphify: Hands-On Guide (2026)
AI

Cut Claude Code Tokens 71x with Graphify: Hands-On Guide (2026)

Make Claude Code read a knowledge graph instead of grepping every file. Install Graphify, compile your codebase + PDFs + docs, and shrink per-query tokens 10x — full walkthrough.

Read
Claude Opus 4.7 Review: Benchmarks, Pricing, GPT-5 Comparison
AI

Claude Opus 4.7 Review: Benchmarks, Pricing, GPT-5 Comparison

Claude Opus 4.7 benchmarks, pricing, GPT-5.4 and Gemini 3.1 Pro comparison, xhigh mode, and the real 1.35x tokenizer cost issue explained.

Read
Beyond RAG: Karpathy's LLM Wiki Pattern Explained (2026)
AI

Beyond RAG: Karpathy's LLM Wiki Pattern Explained (2026)

Hit RAG's limits? Andrej Karpathy's LLM Wiki pattern is a markdown-first alternative — 3-layer architecture, 95% token savings, exploding ecosystem in 2 weeks.

Read
Claude Code Review: Complete Guide (2026)
AI

Claude Code Review: Complete Guide (2026)

Honest Claude Code review covering installation, pricing, vs Cursor, pros and cons — everything in one post.

Read
Gemma 4 Review: Benchmarks, Multilingual, Local Setup
AIGuides

Gemma 4 Review: Benchmarks, Multilingual, Local Setup

Gemma 4 model lineup, benchmarks, Llama 4 vs Qwen 3.5 comparison, multilingual performance, and Ollama local setup in one guide.

Read

A small favor 🙏

Ads keep TechJupJup free. If you don’t mind, please consider turning off your ad blocker — it really helps us keep the articles coming.