What exactly prevents anyone worried about this to build an LLM that can decode the neuralese to english and use it to monitor what the model is doing?
Or is the neuralese some sort of irreversibly encrypted data set that only an LLM can "understand" and that can never be translated back to English?
Or is the neuralese some sort of irreversibly encrypted data set that only an LLM can "understand" and that can never be translated back to English?