AI evaluations can establish lower bounds on capabilities but cannot establish upper bounds, forecast future capabilities robustly, or assess misalignment risk, so they should not be the primary basis for AI safety decisions.
Frontier Safety Framework, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
What AI evaluations for preventing catastrophic risks can and cannot do
AI evaluations can establish lower bounds on capabilities but cannot establish upper bounds, forecast future capabilities robustly, or assess misalignment risk, so they should not be the primary basis for AI safety decisions.