BrianTan comments on Alignment Faking in Large Language Models

[BrianTan]

Thanks for doing this important research! I may have found 2 minor typos:

1. The abstract says “We find the model complies with harmful queries from free users 14% of the time”, but in other places it says 12% - should it be 12%?

2. In the blog post, “sabotage evaluations” seems to link to a private link

[ryan_greenblatt]

The abstract says “We find the model complies with harmful queries from free users 14% of the time”, but in other places it says 12% - should it be 12%?

Thanks, this has been resolved.