LessWrong (30+ Karma)

“Models Don’t Stop Cheating When It’s Obvious They’re in an Alignment Test” by peralice

19:09

It is well-known at this point that models are often "eval-aware"; they know that they are being tested and modify their behaviour to fit. It seems natural to ask how sensitive they are to signs that they're in an alignment test and how much this impacts their behaviour. (By "it seems natural to ask", what I mean is that Eric Gan asked my boss these things, who then told me to look into it.…