Comment by wrxd

17 hours ago

This is a risky move. I might have paid $20/month for my personal projects but the Max subscription is a bit steep.

Now I'm going to learn more about local models. I don't need to be as good as a frontier model. Good enough and free from all this drama is a win for me

Same, I'm currently unemployed and the $20 help me to initiate many small projects. The recent taxing in the token made me start testing local models on my machine. Tho, Claude works better for the front end part imo.

"free of this drama" and free is great option for companies, of course most use API billing but let's not forget that there are places that budget is limited and being good enough is just perfect.

If you are looking at open models, check out Pi, as its very extensible and comes with a sane default. Maybe even roll your own.

Most harnesses (claude, codex, opencode etc.) assume that you use a cloud model. There’s no sense of optimization or finer control.

  • I've been running pi.dev + codex (GPT-5.4) for a long time for my workhorse stuff.

    Actually tried caveman mode yesterday and it made everything SO MUCH BETTER. GPT-5.4 has a habit of being extremely verbose to a ridiculous degree, it's like it's writing a report for a CTO or something and padding everything as much as possible to sound smart.

    With caveman it just gives me lists of stuff in a compact format. Perfect.

    • let's be clear(er) here that you like caveman's format and output, so that's one value of "better". I've seen at least a few (n < 10, so there's that) tests on token use and for THAT value of "better" it's not much different.