Towards Human-AI Complementarity for AI Safety
Safely overseeing AI is increasingly challenging for the humans doing it, as they must evaluate longer and more complex outputs with every new model generation. To mitigate this challenge, we could leverage complementarity: where humans and models make different mistakes, combining their judgements could yield an overs...
S.-X. Shi, M. Christ, Eric Modesitt et al.
· 0 citations