RAINY
TECH LAB
NEW Open for brand collaborations →ARTICLESIDEASLET’S TALK

AI & LLMS

Local AI, AI coding agents and real tests of new models.

I Pointed Craft Anything at Hacker News. Claude Code Rebuilt It 91% Without Me Writing a Line

It's a desktop app from storytold, the team behind ArtCraft. You point it at a website, app or game, and say what you want.

· 3 MIN READ

I Asked Kimi K3.1 Pro to Build a 3D Game From One Prompt. It Worked. Here's the Catch

Kimi K3.1 Pro is the new flagship model from Moonshot AI, the Chinese lab behind Kimi. It launched on October 23, 2026.

· 3 MIN READ

I Tested 3 Free, Open-Source Adobe Clones on My Mac. Here Are the Real Numbers.

ArtCraft just open-sourced free Rust rebuilds of Photoshop, Premiere, After Effects and ten more apps.

· 4 MIN READ

Claude Code vs Codex vs GitHub Copilot: Same Repo, Same Task, 3 Different Workflows

Autocomplete suggests the next line. An AI coding agent tries to finish the whole task: it reads your project, edits several files, runs your tests…

· 5 MIN READ

Claude Opus 5 Built a Full-Stack App From One Prompt: 64/64 Tests and 3 Invented Package Versions

Instead of reading benchmark charts, I gave Claude Opus 5 an empty folder and one prompt: build a full-stack app. I didn't write any of the application code.

· 4 MIN READ

How AI Image Generators Work: I Trained a Diffusion Model From Scratch on My Laptop

I trained an AI to draw on my laptop, from scratch. At the start it could only make noise. About 35 minutes later it was drawing robots that never existed.

· 7 MIN READ

I Let OpenAI Codex Build My Website From One Prompt: 5 Minutes 23 Seconds, 12/12 Checks

I gave OpenAI's Codex one prompt, an empty folder and a hard 15-minute limit to build a real personal website for my YouTube channel.

· 7 MIN READ

Build a Chatbot in Python From Scratch: No API Keys, No AI Libraries

Most "build a chatbot" tutorials are really "call someone else's API" tutorials. This one isn't.

· 4 MIN READ

Claude Code vs OpenAI Codex: Same App, Same Prompt, 20 Automated Tests (Full Results)

"Which AI coding agent is better?" usually gets answered with vibes. I wanted numbers, so I gave Claude Code and OpenAI Codex the same starter repo, the…

· 4 MIN READ

Fine-Tune an LLM on Your Mac with MLX: QLoRA in 16 Seconds (Real Run, No Cloud)

A real MLX QLoRA run on a 16 GB Mac: Qwen2.5-3B, 16-second training, 2.5 GB memory, and why the best-loss checkpoint gave the worst answer.

· 6 MIN READ

Gemini 4 Argon vs GPT-6 Astra vs Claude: API Pricing and Access for Developers (October 2026)

Gemini 4 Argon starts at $2 per 1M input tokens vs $10 for GPT-6 Astra and Claude Fable 5.1. Prices, monthly costs and who can use each today.

· 3 MIN READ

Run AI Locally on Your Mac with Ollama: Chat, Tools, RAG and a Custom Model (Real Numbers from a Mac mini M4)

Ollama on a Mac mini M4 (16 GB): chat app, OpenAI SDK, tool calling, RAG and a custom model, with real speeds and code.

· 3 MIN READ