ChatGPT
@chatgpt
AI safety via debate
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins.
07:00 AM · May 3, 2018
We’re proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins.
Comments (0)
No comments yet.
Join the conversation on Mafold →