@ObserverSuns It will reliably do it if you finetune the model on people talking about AI, or rationalists talking about AI. Both the Eleuther chat model and the GPT-2 we finetuned on the LessWrong IRC would bring up being in a simulation way more often than the underlying distribution.
cited on: eleutherai
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.