> If I don't use AI to build my own SaaS / business
This was going to burn you out no matter what, unless you got the business chops and the stamina to be in it for the long term.
My advise: stay at your job and ride this wave, don't try to go under it. To countrbalance, work on hobby projects that scratch an itch for you. Work at your own pace for fun, not for profit. The value you get out of it is satisfaction rather than money (which is what your day job is for).
- Claude Opus for general discussion, design, reviews, etc.
- Codex GPT-5.4 High for task breakdown and implementation.
I often feed their responses to each other (manual copy/paste) to validate/improve the design and/or implementation. The outcome has been better than using one alone.
This workflow keeps Claude's usage in check (it doesn't eat as much tokens), and leverages Codex generous usage limits. Although sometimes I run into Codex's weekly limit and I need to purchase additional credits: 1000 credits for $40, which last for another 4-5 days (which usually overlap with my weekly refresh, so not all the credits are used up).
There seem to be two fundamentally incompatible interpretations of "Never again" [1]. I thought it was a no brainer for universal adoption, but TIL that for some it means more of the same.
It's a shame that such a good product is tarnished with reliability and capacity issues. I hope they get their act together, otherwise trust is eroding by the day.
Interesting take on enforcing state machine rules using a proof system. I'm interested in this space, and have been developing a new programming language to enable typestate / state-machine representation at the type system level[0].
I don't know where it will end up on the spectrum of systems languages; it may end up being too niche or incomplete, but so far I think I'm scratching the right itch, at least for myself.
I miss the days when "API" meant any programming interface - not just web/rpc - and good API design was about providing the right level of abstraction and making doing the right thing easy and the wrong thing hard, not just CRUD.
reply