<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Tech Jupjup</title><description>Handpicked AI &amp; Tech — Tested, Reviewed, Delivered</description><link>https://techjupjup.com/</link><language>en-US</language><item><title>What Is Vectorless RAG? Is PageIndex a Real RAG Alternative?</title><link>https://techjupjup.com/en/ai/pageindex-vectorless-rag-review/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/pageindex-vectorless-rag-review/</guid><description>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.</description><pubDate>Thu, 07 May 2026 00:00:00 GMT</pubDate><category>PageIndex</category><category>vectorless RAG</category><category>RAG alternative</category><category>MCP</category><category>document retrieval</category></item><item><title>Best Local AI Server for Mac? Rapid-MLX Install, Performance, and Ollama Comparison</title><link>https://techjupjup.com/en/ai/rapid-mlx-local-ai-server/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/rapid-mlx-local-ai-server/</guid><description>A current guide to what Rapid-MLX actually is, how to run it on a Mac, and how it compares with Ollama, LM Studio, and mlx-lm serve.</description><pubDate>Wed, 06 May 2026 00:00:00 GMT</pubDate><category>Rapid-MLX</category><category>MLX</category><category>Apple Silicon</category><category>local LLM</category><category>Ollama</category></item><item><title>What Is PlayMCP? Kakao&apos;s MCP Hub and OpenClaw Integration Explained</title><link>https://techjupjup.com/en/ai/playmcp-openclaw-guide/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/playmcp-openclaw-guide/</guid><description>A current guide to what PlayMCP really is, how Kakao&apos;s toolbox and mcp-gateway work, and why the OpenClaw integration matters.</description><pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate><category>PlayMCP</category><category>OpenClaw</category><category>Kakao MCP</category><category>AI agents</category><category>MCP</category></item><item><title>How to Use NotebookLM in 2026: Free Limits, Upgrade Triggers, and Gemini Workflow</title><link>https://techjupjup.com/en/guide/notebooklm-guide-gemini-workflow/</link><guid isPermaLink="true">https://techjupjup.com/en/guide/notebooklm-guide-gemini-workflow/</guid><description>A practical NotebookLM guide covering free limits, Deep Research, Gemini Notebooks, file generation, privacy caveats, and when to upgrade.</description><pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate><category>NotebookLM</category><category>Gemini</category><category>Gemini Notebooks</category><category>AI research</category><category>document generation</category></item><item><title>Recordly Review: A Free Screen Studio Alternative With Auto Zoom, GIF Export, and Korean UI</title><link>https://techjupjup.com/en/guide/recordly-screen-recorder-review/</link><guid isPermaLink="true">https://techjupjup.com/en/guide/recordly-screen-recorder-review/</guid><description>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.</description><pubDate>Sun, 03 May 2026 00:00:00 GMT</pubDate><category>Recordly</category><category>screen recorder</category><category>Screen Studio alternative</category><category>open source</category><category>auto zoom</category></item><item><title>Andrej Karpathy&apos;s 4 AI Coding Warnings and the 100K-Star CLAUDE.md Repo</title><link>https://techjupjup.com/en/ai/andrej-karpathy-skills-review/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/andrej-karpathy-skills-review/</guid><description>A deep dive into the four bad AI coding habits Karpathy warned about, the CLAUDE.md repo&apos;s four operating principles, what evidence supports them, and where the limits still are.</description><pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate><category>CLAUDE.md</category><category>Claude Code</category><category>AI coding agents</category><category>Cursor rules</category><category>Codex</category></item><item><title>LG EXAONE 4.5 and the Real State of Korean Local LLMs</title><link>https://techjupjup.com/en/ai/exaone-4-5-korean-local-llm/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/exaone-4-5-korean-local-llm/</guid><description>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.</description><pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate><category>EXAONE 4.5</category><category>Korean local LLM</category><category>HyperCLOVA X</category><category>Kanana 2</category><category>A.X 4.0</category></item><item><title>Oh My OpenAgent Review: A Multi-Agent Alternative to Claude Code (2026)</title><link>https://techjupjup.com/en/ai/oh-my-openagent-review/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/oh-my-openagent-review/</guid><description>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.</description><pubDate>Thu, 30 Apr 2026 00:00:00 GMT</pubDate><category>Oh My OpenAgent</category><category>OpenCode</category><category>Claude Code alternative</category><category>AI coding agents</category><category>multi-agent</category></item><item><title>Qwen 3.6 27B Review: A Local Coding Agent Tested on RTX 4090 and M4 Max (2026)</title><link>https://techjupjup.com/en/ai/qwen-3-6-review/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/qwen-3-6-review/</guid><description>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.</description><pubDate>Thu, 30 Apr 2026 00:00:00 GMT</pubDate><category>Qwen 3.6</category><category>local coding agent</category><category>RTX 4090</category><category>open-weight LLM</category><category>Apache 2.0</category></item><item><title>AI Apps Are Built with Harnesses, Not Prompts</title><link>https://techjupjup.com/en/ai/harness-engineering-ai-apps/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/harness-engineering-ai-apps/</guid><description>A practical guide to harness engineering: context, tools, evals, observability, CI gates, and security for production AI apps.</description><pubDate>Sat, 25 Apr 2026 00:00:00 GMT</pubDate><category>Harness Engineering</category><category>LLM Evaluation</category><category>AI Agents</category><category>LLMOps</category><category>AI App Testing</category></item><item><title>GPT-5.5 Review: Benchmarks, Pricing, Codex Impact, and Early Reactions (2026)</title><link>https://techjupjup.com/en/ai/gpt-5-5-review/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/gpt-5-5-review/</guid><description>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.</description><pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate><category>GPT-5.5</category><category>OpenAI</category><category>AI model comparison</category><category>Codex</category><category>AI coding</category></item><item><title>HOP HWP Desktop App Guide 2026: Open HWP and HWPX on Mac, Windows, and Linux for Free</title><link>https://techjupjup.com/en/guide/hop-hwp-open-desktop-app/</link><guid isPermaLink="true">https://techjupjup.com/en/guide/hop-hwp-open-desktop-app/</guid><description>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.</description><pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate><category>HOP</category><category>HWP viewer</category><category>Hancom alternative</category><category>desktop HWP app</category><category>Mac HWP</category></item><item><title>GLM 5.1 Review: Run Claude Code at 1/5 the Price with Open-Weight SOTA</title><link>https://techjupjup.com/en/ai/glm-5-1-review/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/glm-5-1-review/</guid><description>How to run GLM 5.1 in Claude Code at one-fifth the cost, plus what Z.AI&apos;s official docs reveal about subscription-backed API access, Vision MCP, and GLM-Image.</description><pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate><category>GLM 5.1</category><category>Z.AI</category><category>Claude Code</category><category>open-weight LLM</category><category>AI coding</category></item><item><title>Kimi K2.6 Deep Dive: 88% Cheaper Claude Opus 4.7 Alternative?</title><link>https://techjupjup.com/en/ai/kimi-k2-6-deep-dive/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/kimi-k2-6-deep-dive/</guid><description>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.</description><pubDate>Wed, 22 Apr 2026 00:00:00 GMT</pubDate><category>Kimi K2.6</category><category>Moonshot AI</category><category>open-weight LLM</category><category>AI coding</category><category>Claude Code alternative</category></item><item><title>Cut Claude Code Tokens 71x with Graphify: Hands-On Guide (2026)</title><link>https://techjupjup.com/en/ai/graphify-guide/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/graphify-guide/</guid><description>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.</description><pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate><category>Graphify</category><category>Claude Code</category><category>knowledge graph</category><category>GraphRAG</category><category>LLM Wiki</category></item><item><title>Claude Opus 4.7 Review: Benchmarks, Pricing, GPT-5 Comparison</title><link>https://techjupjup.com/en/ai/claude-opus-4-7/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/claude-opus-4-7/</guid><description>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.</description><pubDate>Sun, 19 Apr 2026 00:00:00 GMT</pubDate><category>Claude</category><category>Claude Opus 4.7</category><category>Anthropic</category><category>AI coding</category><category>GPT-5 comparison</category></item><item><title>Beyond RAG: Karpathy&apos;s LLM Wiki Pattern Explained (2026)</title><link>https://techjupjup.com/en/ai/karpathy-llm-wiki/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/karpathy-llm-wiki/</guid><description>Hit RAG&apos;s limits? Andrej Karpathy&apos;s LLM Wiki pattern is a markdown-first alternative — 3-layer architecture, 95% token savings, exploding ecosystem in 2 weeks.</description><pubDate>Sun, 19 Apr 2026 00:00:00 GMT</pubDate><category>RAG alternative</category><category>LLM knowledge base</category><category>Karpathy LLM Wiki</category><category>personal knowledge management</category><category>AI architecture</category></item><item><title>How to Open HWP Files Without Hancom in 2026: Free RHWP Chrome Extension</title><link>https://techjupjup.com/en/guide/rhwp-hwp-chrome-extension/</link><guid isPermaLink="true">https://techjupjup.com/en/guide/rhwp-hwp-chrome-extension/</guid><description>Open HWP files on Mac, Linux, Windows, or Chrome without Hancom Office. RHWP is a free open-source Chrome extension with local WASM processing and basic editing.</description><pubDate>Sat, 18 Apr 2026 00:00:00 GMT</pubDate><category>HWP viewer</category><category>Hancom alternative</category><category>Mac HWP</category><category>Chrome extension</category><category>RHWP</category></item><item><title>Claude Code Review: Complete Guide (2026)</title><link>https://techjupjup.com/en/ai/claude-code-review/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/claude-code-review/</guid><description>Honest Claude Code review covering installation, pricing, vs Cursor, pros and cons — everything in one post.</description><pubDate>Sat, 11 Apr 2026 00:00:00 GMT</pubDate><category>Claude Code</category><category>AI coding tools</category><category>vibe coding</category><category>Cursor comparison</category><category>Anthropic</category></item><item><title>Gemma 4 Review: Benchmarks, Multilingual, Local Setup</title><link>https://techjupjup.com/en/ai/gemma4-review/</link><guid isPermaLink="true">https://techjupjup.com/en/ai/gemma4-review/</guid><description>Gemma 4 model lineup, benchmarks, Llama 4 vs Qwen 3.5 comparison, multilingual performance, and Ollama local setup in one guide.</description><pubDate>Sat, 11 Apr 2026 00:00:00 GMT</pubDate><category>Gemma 4</category><category>open source AI</category><category>local LLM</category><category>Ollama</category><category>AI model comparison</category></item></channel></rss>