I’ve only read the blog post and a bit of the paper so far, but do you plan to investigate how to remove alignment faking in these situations? I wonder if there are simple methods to do so without negatively affecting the model’s capabilities and safety.
I’ve only read the blog post and a bit of the paper so far, but do you plan to investigate how to remove alignment faking in these situations? I wonder if there are simple methods to do so without negatively affecting the model’s capabilities and safety.