ohhhh i get it now, so Al writes all the code and i shouldn't care to look at it because the code passes a set of very strict constraints that Al also wrote. makes sense.
Excellent software takes time.
It requires smart people to care deeply about the product and to obsess over the details. To debate passionately about the details big and small. To spend time deeply thinking.
Nothing about this has changed.
please i'm begging you show me something you built
not another "this is my custom agent setup" post where you pretend you're doing something smarter than vanilla claude code
please
He asks the wrong questions:
It shouldn't be "How are you supposed to review 5k lines of code every day?"
Instead: Are the 5k lines of code per day valuable? If they're not, the question of review is moot.
It shouldn't be: "Why people that now protest against AI were not horrified by the state of software in the last decade?"
Instead: Why as an "engineering" field are we happy to accept innovation making the quality of software steadily decrease decade after decade?
I do not understand defenders of status quo philosophies in software development. Even if you don’t think software quality has deteriorated at all in the past several decades (in some ways it hasn’t, but in numerous ways it objectively has), you have to lack all imagination or analytical abilities to consider modern software as the pinnacle of what could be produced.
Software can be much better than it is. I’m not interested in your methodologies which have led to many decades of slop (both pre- and post-LLM). I’m not interested in producing status quo results, even if it’s faster than it used to be. I care about what I make.
In a 3% experiment, removing the Top-30 highest paid revenue share accounts from the For You timeline increased both time spent and daily active users on X.