That sounds like a good idea, but shipping 10x as many features and bugfixes sounds better.
I started using AI with the best intentions. Checking everything before committing. Improving output by hand if it didn't quite follow the existing code style guidelines or variables were not named as well as they should be. Or if it did something sloppy or hacky.
Now, AI GOES BURRRRRRRRRRRR! If the tests pass it's good to ship. AI can deal with the problems it may create. No problems so far.
Should OP take their mom next time to shut things down for them? You don't have to do what others ask of you, you know. I stand by my original assumption - they were too inexperienced with the world to know you can tell someone no, or lacked the ability to do so.
Well, as someone with autism myself it's relatively easy to spot others, and given the information provided in the post I'd say chances are high. Not sure what rule you're referring to, it looks fine to me - autism is a super power, not a slur.
Yep. This is definitely an OP-is-autistic problem, or is perhaps inexperienced. Not an interviewer problem. Keep it professional. If an interviewer asks a personal question then you simply refuse to answer (politely), or steer it back towards a professional context. If they persist then you end the interview.
This has to be load related. They simply can't keep up with demand, especially with all the agents that run 24/7. The only way to serve everyone is to dial down the power.
The solution, as you say, is probably to break it down into isolated sub-components that are only aware of each other's APIs and nothing more.