ZWQbpkzl [none/use name]

Heat

Basic evolution rules.

You’ll have to be more specific with how anthropic is debuging Firefox. There’s many sort of possible setups. In general though, you’ll need

• an llm model file
• some openai compatible server, eg lmstudio, llama.cpp, ollama.
• some sort of client to that server there’s a myriad of options here. OpenCode is the most like Claude. But there’s also more modular programmatic clients, which might suit a long term task
• the Firefox source code and/or an MCP server via some plugin.

You’ll also need to know which models your hardware can run. “Smarter” models require more ram. Models can run on both CPUs and GPUs but they run way faster on the GPU, if they fit in the VRAM.

Don’t read into the mythos of Ganymede or any of Jupiter’s moons fwiw.

I generally follow the same pattern as you. ~/Code with programming language based sub folders. But there’s also a ~/Code/Work and ~/Code/Orgs which is for code that has a certain purpose. Generally the by-language subfolders are for projects I cloned, not authored. There is a fair amount of symlinking also.

Also /data for long term storage drives. Directories under ~/Audio and ~/Video will usually symlink to there.