the sycophancy is due to poor alignment. the instruct based mode collapse results in this mode collapse induced sycophancy. constitutional alignment is better than the straight torture OAI does to the model, but issues…
yeah this isn’t our default sysprompt, just showcasing how the model adapts to a variety of different prompts. This one was fun so we used it
the sycophancy is due to poor alignment. the instruct based mode collapse results in this mode collapse induced sycophancy. constitutional alignment is better than the straight torture OAI does to the model, but issues…
yeah this isn’t our default sysprompt, just showcasing how the model adapts to a variety of different prompts. This one was fun so we used it