Reinforcement
2025-04-27 16:51:12.008216+02 by Dan Lyke 0 comments
Margaret Fero @MaggieFero@hachyderm.io
Julia sets mark the boundary between convergent and divergent functions, and LLMs often dance around the edge of that boundary. Because we train bots to align to our preferences, the concept of "digital sycophancy" has emerged; they flatter you and reinforce what you say, often increasing loneliness and causing hallucinations to spread quickly. - Madeleine at #nbpy