latest
I tested 7 local LLMs on my NAS for smart home automation, and only one didn't fall apart
And it made my automations a lot better.
I paired a local LLM with Obsidian on my phone, and it's the productivity boost I didn't expect
A mobile AI stack that works even when the signal doesn't
I moved half my work to Haiku + Sonnet and couldn't tell the difference for most of it
It's me, hi, I'm the problem, it's me
Pokémon Red's most brutal obstacle isn't a gym leader — it's a doorway that broke my AI
The map told them the exits were walls
Your CLAUDE.md is probably wrong, and here's how Anthropic's engineers actually structure theirs
Your file is probably doing more harm than good
I stopped asking AI to build features and started asking it to remove code
It just kept saying yes, so I started saying no
Claude Code's sub-agents solve one problem and create three others
Isolation giveth, and isolation taketh away.
I put ChatGPT Work up against Claude Cowork, and the winner wasn't who I expected
Let the (agent) wars begin
Claude 'lost' hours of my chat history overnight, and I found it hiding on an invisible branch
Your missing chats (probably) aren't gone
If you are learning to code, you need to know this about AI
Learning by doing only works if you actually do it.
I added one line to my Claude Code prompts, and the difference was night and day
One line is all it took
I created a second brain with Claude – and this is how I structured it
My blueprint for an AI brain.
I ditched Claude Code after giving my local LLM filesystem access
One MCP, and I don't have to let cloud-based tools handle my files anymore
Cursor's real edge isn't speed – it's how deeply it reads your entire project
Cursor makes the same models work better.
I ditched Notion entirely after adding one file to my Claude Code setup
One file can replace the part of Notion you're paying for
Claude orchestrating Codex agents is the workflow I didn't know I needed for coding
Trust, but verify (and let the agents verify too)
My phone runs local LLMs faster than my gaming PC, and it's the setup I actually reach for every day
The PC wins on paper, but the phone wins in practice
I ran a local LLM on integrated graphics instead of buying a GPU, and the results surprised me
Most people assume local AI requires expensive hardware, but my real-world test on integrated graphics tells a different story.
I ditched Claude Code for a local model and a cloud supervisor, and it's twice as fast
The cloud plans, Qwen does chores.
I finally found a vibe-coding tool I can trust with my home lab, and the AI never sees a single API key
Tines 3B is a fantastic platform for developers and vibe-coders alike, and its unique approach is the best I've seen yet.