Codex CLI felt safer than Claude Code, but it cost me my flow
…When I decided to test it, it was only available for macOS, which made it a natural fit to test on my MacBook before the wider rollout. By doing this, I could…
…When I decided to test it, it was only available for macOS, which made it a natural fit to test on my MacBook before the wider rollout. By doing this, I could…
…If you want to use Ollama and Open WebUI for local LLM usage, you'll want a more powerful CPU and lots of RAM, because StartOS doesn't have GPU passthrough yet…
…problems tested my patience several times. Yet, every hour I spent on that helped me learn how my smart home works. Besides building my devices, I also run a local LLM with…
…Sign in to your XDA account Can " vibe coding " truly democratize game development? This was the central question I was left with after a weekend spent testing the latest iterations of LLMs…
…Related I tested Claude’s new interactive visuals, and they’re changing how I explain things Most LLMs suffer with visualisation, Claude doesn't Another example of how I used Dispatch recently…
…Fabric Interact with all your LLMs without spending too much time perfecting and saving your prompts. See at Github Related I tested Claude Code, Codex, Lovable, and Replit side by side, and…
…Related I replaced Google Home with Home Assistant and a local LLM, and I'm not looking back I've almost retired Google entirely in my home. Ran the numbers and they…
…That's honestly been easier now I have a local LLM to help. It might be a little slow for some tasks, but figuring out YAML or Jinja syntax and why Home…
…I can even see my calendar events alongside my tasks, which is essential for planning a busy week of testing local LLMs or drafting technical guides. OmniFocus OmniFocus is a feature-rich…
…I now use a Paperless-ngx alongside a local LLM on one of my systems, while my old laptop, with merely 4GB DDR3 RAM, runs eight Docker containers. I also have a…