1100 is about where I lose it as well. 1200 I get about half of it with a couple readings. So I could go to about the time of Chaucer's g-g-grandfather.
Oh, people will keep using it no matter how much you warn them.
Proxmox-helper-scripts is a perfect example. They'll agree with you until that site comes up, and then its "it'll never, ever get hacked and subverted, nope, can't happen, impossible".
Any time I've asked for scripts, it's been flawless and way more than I asked for, usually with switches like --host, key, auth etc. But I'm using at least Sonnet if not Opus. I'd punch out a script for you with it but I have nothing that uses SMB in my network to test on.
If you're going to use GPT, you want 5.2-Coder at least, and honestly I'm not as impressed with OpenAI's products as other people seem to be.
Opus 4.6 and GPT 5.3 Codex produce some amazing results if you spend a lot of time scoping, speccing and testing each stage. Just throwing it over the wall with a low-effort prompt isn't going to get you anything that's very good. But time spent on the leadup and close monitoring of the results can give you production-ready code with little tech debt in it, extremely quickly and without a lot of money (energy) spent on inference.
I have an Emporia Vue CT monitor that watches all my lines right at the box. IDK about newer versions, but the old version could be hacked so you don't have to use their shitty app.
Is it below 50,000 so we can investigate pedos again?