Chris Olah urges deeper thought on personas as central safety object
Original titleI think it's worth thinking long and hard about it. "If personas were the central object of safety, what should we do?"
AISummary
Anthropic-affiliated researcher Chris Olah suggests the community think long and hard about whether personas should be the central object of AI safety. He poses the question of what should be done if that were the case, without offering a specific answer or proposal.
Source: Chris Olah · x.comPublished · added here