Posts

This was borrowed from https://til.simonwillison.net/claude-code/playwright-mcp-claude-code which is currently responding with a 502, so I wanted to also place it here for my own notes Using Playwright MCP with Claude Code Inspired by Armin, I decided to figure out how to use the official microsoft/playwright-mcp Playwright MCP server with Claude Code. Short version: run this before starting claude: claude mcp add playwright npx ‘@playwright/mcp@latest’ That’s it! Now when you run claude Playwright will be available. You can say things like: ...

Setting up Gluetun for Ollama It all started with wanting to have a pod use a Wireguard connection to be able to reach something on the Wireguard VPN network. It led to this rabbit hole of research, to figure out how to get Gluetun, Wireguard, and Talos to all play nicely together. It took me way longer than I would’ve liked or expected, so I wanted to document it here in case someone else could benefit from it. ...

I struggled muddling through all the forum posts for the best way to replace a ZFS drive in Proxmox, so here are my documented notes for how to do so - if you ever need to unfortunately do so. So you’ve got an email like the one above, and it’s time to replace the drive in your ZFS pool in Proxmox. Let’s go through how to find the drive that’s dying, replacing it, matching the parititons of the other drives, and getting it to resilver. ...

I’ve recently dove headfirst into running LLMs on my local hardware, and I wanted to share what I’ve learned and how I’ve set it up so others that want to do the same thing, may. If you’re on a Windows Desktop machine, and you just want to interact with LLMs on your desktop, then skip to the section about installing Ollama. Hardware When it comes to the hardware, I utilized my media PC that had mostly been sitting dormant. This PC has a 5700X and RTX 3070 Ti, which is more than enough to get started. As of now in 2024, it’s still a great time to build a PC using new or used parts. If you need to brushup on how to build a PC, LTT created a great video here. I’ve found that most LLMs < 10B parameters (which we’ll talk about later) only need ~8GB of VRAM. So if you’re able to secure a GPU that has that amount of VRAM or less, you’ll be in a great spot. ...

Hey all, I just picked up a Raspberry Pi 4 Model B, and finding this information wasn’t easy. I wasn’t able to have any success with StackOverflow or anything of the sort either. So here’s what you need to do. I used the image of Raspbian located at this link. Without SSH access If you don’t have SSH access, you can simply plugin your display adapters, keyboard and mouse, and spawn a shell. The icon can be found in the top left of your screen if following this guide with a fresh install of Raspbian. ...