AI on Geoff Corey's Blog

Missile Command coded by Qwen 3.6 with Claude CLI using the local LLM

Wed, 22 Apr 2026 00:00:00 +0000

I wanted to try pointing Claude CLI to a local LLM and see how well it would work. My machine is running linux EndevourOS has the following specs:

Monitor     3840x2160 in 27", 60 Hz [External]
Monitor     3840x2160 in 32", 60 Hz [External]
CPU         12th Gen Intel(R) Core(TM) i9-12900KF @5.20 GHz 52.0°C
GPU         AMD Radeon RX 9070 - 48.0°C [Discrete]
G Driver    amdgpu
Vulkan      1.4.335 - radv [Mesa 26.0.5-arch1.1]
Motherboard PRIME Z690M-PLUS D4 (Rev 1.xx)
Bios        3811 (38.11)
RAM         ●●●● 23.94 GiB / 62.60 GiB (38%)

I use llama-cpp to run the model locally. During this experiment I kept hitting the context limit. I bumped it pretty high but then again, I have plenty of memory.

Migrating from Ghost to Hugo using Claude

Sun, 05 Apr 2026 00:00:00 +0000

Decided to move my blogs from Ghost to using Hugo and generate a static website for the content. The reason for this was I don’t use all the fancy features of Ghost. I don’t do newsletters and Ghost requires an email account if people want to sign up for notifications. Plus I have to run a database for the content.

I started with creating an new directory and fired up Claude and started with this initial prompt.

Coding with Claude AI

Wed, 21 Jan 2026 00:00:00 +0000

So I wanted to see what AI coding can do and started claude with /plan

Make a clone of Bejeweled game to run on Linux

It laid out the requirements, made a to-do list and suggested Rust + bevy for the implementation. I agreed. It asked would you like me to build it and off we go.

Initial commit didn’t have tests, executed but the grid for the gems was offset. I looked at the code and figure the something was a miss with the layout and asked Claude

Gemini Coding

Sat, 20 Dec 2025 00:00:00 +0000

Continue to play with various AI’s and how to use them in code generation. Next up is Gemini. I installed gemini-cli and setup an API key on Google along with a billing account and limit. See https://aistudio.google.com

Next I decided to try something that isn’t common (to-do, note taking, etc) and build a Texas Holdem Poker API server. I wasn’t sure the best way to write prompts and have been reading some books on the matter. I decided to ask Proton’s Lumo AI with the prompt, “help me write a prompt to build the API for a texas holdem poker game”