RLAIF Experimentation Collection Research into RLAIF (Reinforcement Learning from AI feedback) with the goal of Constitutional AI and Sycophancy Resistance. • 4 items • Updated about 14 hours ago
RLAIF Experimentation Collection Research into RLAIF (Reinforcement Learning from AI feedback) with the goal of Constitutional AI and Sycophancy Resistance. • 4 items • Updated about 14 hours ago