latest
I used Claude Code, Codex, and Google Antigravity to build my dream note-taking app, and one is in a different league
Apparently “build me a notes app” means three very different things
I pointed Claude Code at my Obsidian vault, and it became the second brain I never had the discipline to build
It's less of a second brain and more an extension of mine
I paired this Uptime Kuma killer with local LLMs, and monitoring my Proxmox servers has never been easier
The best part? Everything runs locally!
When GPT-6 Astra started losing at StarCraft, it just stole the winning bot instead of playing fair
Like a real gamer, OpenAI's GPT-6 Astra wanted to win at all costs.
5 open-source local AI tools nobody talks about, but they deserve way more attention
These lesser-known open-source tools are changing how I use AI on my own hardware.
My home lab finally has an AI brain, and it's Claude Code through MCP
Claude Code + Home Assistant is brilliant combo.
I set up Claude Code the way Spotify does to save tokens, and it cost me more
This wasn't the expected result, but perhaps something changed in Claude's models since Spotify wrote up its findings
I replaced ChatGPT, Claude, Gemini, and Perplexity with free open-source alternatives
My bank can finally breathe
After a month switching between Claude Code and its open-source rival, I only open Claude for one kind of task
Some folders don't get to be test runs
I replaced Grammarly with a local LLM, and none of my writing leaves my laptop anymore
My proofreader lives on my laptop now
Google AI Plus and free users are losing access to Gemini models, and it's happening very soon
The more advanced tiers aren't seeing any changes.
Claude Code's desktop GUI has one superpower the terminal version will never match
Same engine, different experience
I compared my Claude Code workflow to a beginner's, and some of my habits were making things worse
Oops. Accidentally optimized my Claude Code setup backwards.
Gemini is getting rid of Gems, and its replacement aims to make repetitive work a lot easier
It introduces some key new features that make them better than Gems.
I ran a local LLM on my phone for a month, and it handled 90% of the prompts I used to send to Claude and ChatGPT
Most of my prompts never needed the cloud
I gave my local LLM a nearly-full SSD and told it to find everything I could safely delete
Could Qwen3.6 beat my incessant clutter?
Claude finally got me to stop procrastinating, and it only took one instruction
The problem with asking AI for help, solved
Linux kernel maintainers just wrote the playbook for shipping AI-generated code without drowning in slop
Make sure you know what your AI is coding.
I run Claude, ChatGPT, and my local LLM through one interface, and I'm not going back
One window instead of three