Mr. McGuire: I just want to say one word to you. Just one word.

Benjamin: Yes, sir.

Mr. McGuire: Are you listening?

Benjamin: Yes, I am.

Mr. McGuire: Plastics.

Benjamin: Exactly how do you mean?

Mr. McGuire: There’s a great future in plastics. Think about it. Will you think about it?

A great future they said. 😭

Give Andy Yen a re-interview by Proton Customers and see if he passes

This one stood out to me.

I started off with Ollama, but liked llama.cpp better because you can download one GGUF file the day it’s released and add it to a source controlled config.ini with parameters to make it work best on your hardware.

I didn’t get serious about local LLMs until I realized I could run Qwen 3.6 35B-A3B on my 3070 with q4 for KV cache and get over 100k context. I found Ollama’s Modelfile approach and model handling in general to be clunky and discouraging important tweaks, but llama.cpp keeps everything simple.

Mint is good if OS tinkering isn’t where you want to spend your time and you want something with sane defaults that just works. Immutable distros like Bazzite, Aurora, or SteamOS are arguably more newb-friendly and turn-key, whereas Mint is more readily customized (and broken).

McDonald’s can probably make hamburgers more efficiently than everyone can at home, but I’m not eating that shit any more than I’m giving Sam Altman my money or data.