the startup time is crazy, you can start writing as soon as you hit the command
(I don't use codex, just noticed that it's crazy fast)
If you want to go further, you can even require the LLM to produce a machine checkable proof that the software is correct. That's beyond the state of the art at the moment, but it's far from 'unsolvable'.
If you hallucinate such a proof, it'll just not work. Feed back the error message from the proof checker to your coding assistant, and the hallucination goes away / isn't a problem.
Also tests and proof checkers only catch what they’re asked to check, if the LLM misunderstands intent but produces a consistent implementation+proof, everything “passes” and is still wrong.
Deleted Comment
But 2025 was maybe down to 90% pain-free, and I want to get stronger. So I did a big rewrite of my entire workout plan and checked everything. AI wasn't perfect, but it was amazing when you already know some.
It is still a tool I had to direct, and it took a few days of work. But I'm amazed at where it got me to. It took the injury into consideration and my main sport, and built around that. In the past I tried do this online and couldn't do it given the numerous factors involved. It was not perfect, but over the course of a few days, I was able to sort it out (and test with a trainer on the approach a few weeks after).
I've been 100% pain free for 6 weeks in a way I haven't felt in a long time.
Was it something unexpected like "exercise this seemingly unrelated muscle group that has nothing do with your injury but just happens to reduce pain by 75% for some inexplicable reason"?
Or was it something more mundane like "instead of exercising this muscle every day, do it every other day to give it time to rest"?