And as a follow-up in case the current sleeper agent does admit when it’s doing something dangerous: I’d be interested whether you can train a sleeper agent that never admits it’s doing something dangerous if the “2024” trigger is in the prompt (even if after backdoor insertion, the blue team finetunes it to answer truthfully in cases with dangerous code but without the presence of that trigger). For such a sleeper agent, you could again check whether a probe works.
And as a follow-up in case the current sleeper agent does admit when it’s doing something dangerous: I’d be interested whether you can train a sleeper agent that never admits it’s doing something dangerous if the “2024” trigger is in the prompt (even if after backdoor insertion, the blue team finetunes it to answer truthfully in cases with dangerous code but without the presence of that trigger). For such a sleeper agent, you could again check whether a probe works.