Models Often Don't Stop Cheating When It's Obvious They're in an Alignment Test
By now there is a large amount of anecdotal and empirical evidence that models are "eval-aware"; i.e. have the ability to infer when they are being tested and modify their behaviour accordingly. At work we have a database of evaluations that induce misaligned behaviour, and it seemed natural to actually test how sensitive they are to signs that they're being evaluated for alignment, and how much this impacts their behaviour.[1] (By "it seemed natural to test", what I mean is that Eric Gan asked ...
Read full article →