Relevant paper discussing risks of risk assessments being wrong due to theory/model/calculation error. Probing the Improbable: Methodological Challenges for Risks with Low Probabilities and High StakesBased on the current vibes, I think that suggest that methodological errors alone will lead to significant chance of significant error for any safety case in AI.
Relevant paper discussing risks of risk assessments being wrong due to theory/model/calculation error. Probing the Improbable: Methodological Challenges for Risks with Low Probabilities and High Stakes
Based on the current vibes, I think that suggest that methodological errors alone will lead to significant chance of significant error for any safety case in AI.