Bounding eval awareness of ~human-level AI across the safe-to-dangerous shift

·LessWrong··

In our last post, we argued that measuring evaluation awareness is fundamentally challenging because of the safe-to-dangerous distributional shift: we cannot directly measure the evaluation awareness of a model without deploying it, but we cannot safely deploy it until we know it is not scheming. We expect sufficiently superhuman AI will be eval aware, but this post outlines a tentative solution for bounding the awareness of a ~human-expert-level[1] AI across this safe-to-dangerous shift:Instead...

Read full article →

Related Articles

Unauthenticated remote code execution in Nginx
speedping · Hacker News · 1d ago
Cooling buildings is overtaking heating them as an energy need, IEA says
robtherobber · Hacker News · 8h ago
Ruby2ßhell: Pre-authentication RCE on stock Rails
jdns · Hacker News · 18h ago
Pancreatic cancer halted by virus injection in three patients
cybermango · Hacker News · 5h ago
Highly classified US national security communications network goes down
monkeydust · Hacker News · 2d ago