"Thomas Kwa's MIRI research experience" by Thomas Kwa and others
LessWrong (Curated & Popular)
00:00
Agent Reflection and Research Feedback
This chapter discusses the challenges of agent reflection and the potential consequences of an agent being taken over by subagents or changing its priorities. They also explore ways to improve feedback loops for research, focusing on both training and on-the-job work.
Play episode from 15:59
Transcript
